Hierarchical RL

RL: Reinforcement Learning

Follow this topic Ask about this topic

Hierarchical reinforcement learning helps agents handle long tasks by grouping primitive actions into skills or planning through intermediate goals. Common approaches include options and manager-worker policies, learned subgoal selection, action chunking, offline skill reuse, and model-based planning. These methods are applied to sparse-reward control, robotics, multi-agent coordination, and language-model agents, where they can improve exploration, credit assignment, and transfer. A central challenge is learning abstractions that are useful and stable without hand-designed boundaries, while keeping high-level plans aligned with what low-level controllers can reliably execute.

Latest papers

160 papers25 papers in the last four weeks, up 32% on the four weeks before. 0.1% of all new papers.

Apr 13, 2026

Hierarchical RL-MPC Control for Dynamic Wake Steering in Wind Farms

Wind farm wake steering optimization is challenging due to complex flow physics and changing conditions. This paper presents a hierarchical framework that combines reinforcement learning with model predictive control, where an RL agent learns compensatory state estimates for an MPC controller, rather than directly controlling turbines. Evaluated on a three-turbine case, the approach achieves a 23% power gain over the baseline control and surpasses the idealized MPC with perfect state knowledge. Compared to direct RL control, the hybrid architecture maintains superior safety characteristics during training while achieving comparable performance with more stable control actions.

Marcus Binder Nilsen, Teodor Olof Benedict Åstrand, Tuhfe Göçmen +1

Technical University of Denmark, Department of Wind and Energy Systems. Roskilde, Frederiksborgvej 399, Denmark

RL Control Model Predictive Control Hierarchical RL

Apr 10, 2026

Efficient Hierarchical Implicit Flow Q-learning for Offline Goal-conditioned Reinforcement Learning

Offline goal-conditioned reinforcement learning (GCRL) is a practical reinforcement learning paradigm that aims to learn goal-conditioned policies from reward-free offline data. Despite recent advances in hierarchical architectures such as HIQL, long-horizon control in offline GCRL remains challenging due to the limited expressiveness of Gaussian policies and the inability of high-level policies to generate effective subgoals. To address these limitations, we propose the goal-conditioned mean flow policy, which introduces an average velocity field into hierarchical policy modeling for offline GCRL. Specifically, the mean flow policy captures complex target distributions for both high-level and low-level policies through a learned average velocity field, enabling efficient action generation via one-step sampling. Furthermore, considering the insufficiency of goal representation, we introduce a LeJEPA loss that repels goal representation embeddings during training, thereby encouraging more discriminative representations and improving generalization. Experimental results show that our method achieves strong performance across both state-based and pixel-based tasks in the OGBench benchmark.

Zhiqiang Dong, Teng Pang, Rongjian Xu +1

School of Software, Shandong University, Jinan, Shandong, China · Luke EI, Jinan, China

Offline RL Hierarchical RL Representation Learning for RL Flow Matching

Apr 8, 2026

Smart Commander: A Hierarchical Reinforcement Learning Framework for Fleet-Level PHM Decision Optimization

Decision-making in military aviation Prognostics and Health Management (PHM) faces significant challenges due to the "curse of dimensionality" in large-scale fleet operations, combined with sparse feedback and stochastic mission profiles. To address these issues, this paper proposes Smart Commander, a novel Hierarchical Reinforcement Learning (HRL) framework designed to optimize sequential maintenance and logistics decisions. The framework decomposes the complex control problem into a two-tier hierarchy: a strategic General Commander manages fleet-level availability and cost objectives, while tactical Operation Commanders execute specific actions for sortie generation, maintenance scheduling, and resource allocation. The proposed approach is validated within a custom-built, high-fidelity discrete-event simulation environment that captures the dynamics of aircraft configuration and support logistics.By integrating layered reward shaping with planning-enhanced neural networks, the method effectively addresses the difficulty of sparse and delayed rewards. Empirical evaluations demonstrate that Smart Commander significantly outperforms conventional monolithic Deep Reinforcement Learning (DRL) and rule-based baselines. Notably, it achieves a substantial reduction in training time while demonstrating superior scalability and robustness in failure-prone environments. These results highlight the potential of HRL as a reliable paradigm for next-generation intelligent fleet management.

Yong Si, Mingfei Lu, Jing Li +4

School of Aerospace Engineering, Tsinghua University, China · College of Information and Control Engineering, Xi’an University of Architecture and Technology, China · Hangzhou International Innovation Institute, Beihang University, China +2

Hierarchical RL Predictive Maintenance Sparse-Reward RL

Apr 8, 2026

Predictive Representations for Skill Transfer in Reinforcement Learning

A key challenge in scaling up Reinforcement Learning is generalizing learned behaviour. Without the ability to carry forward acquired knowledge an agent is doomed to learn each task from scratch. In this paper we develop a new formalism for transfer by virtue of state abstraction. Based on task-independent, compact observations (outcomes) of the environment, we introduce Outcome-Predictive State Representations (OPSRs), agent-centered and task-independent abstractions that are made up of predictions of outcomes. We show formally and empirically that they have the potential for optimal but limited transfer, then overcome this trade-off by introducing OPSR-based skills, i.e. abstract actions (based on options) that can be reused between tasks as a result of state abstraction. In a series of empirical studies, we learn OPSR-based skills from demonstrations and show how they speed up learning considerably in entirely new and unseen tasks without any pre-processing. We believe that the framework introduced in this work is a promising step towards transfer in RL in general, and towards transfer through combining state and action abstraction specifically.

Ruben Vereecken, Luke Dickens, Alessandra Russo

Computer Science, Imperial College, UK · Information Studies, UCL, UK

Transfer Learning in RL Predictive State Representations Reinforcement Learning State Representation Learning Hierarchical RL

Apr 7, 2026

HiPolicy: Hierarchical Multi-Frequency Action Chunking for Policy Learning

Robotic imitation learning faces a fundamental trade-off between modeling long-horizon dependencies and enabling fine-grained closed-loop control. Existing fixed-frequency action chunking approaches struggle to achieve both. Building on this insight, we propose HiPolicy, a hierarchical multi-frequency action chunking framework that jointly predicts action sequences at different frequencies to capture both coarse high-level plans and precise reactive motions. We extract and fuse hierarchical features from history observations aligned to each frequency for multi-frequency chunk generation, and introduce an entropy-guided execution mechanism that adaptively balances long-horizon planning with fine-grained control based on action uncertainty. Experiments on diverse simulated benchmarks and real-world manipulation tasks show that HiPolicy can be seamlessly integrated into existing 2D and 3D generative policies, delivering consistent improvements in performance while significantly enhancing execution efficiency.

Jiyao Zhang, Zimu Han, Junhan Wang +7

CFCS, School of CS, PKU · National Key Laboratory for Multimedia Information Processing, School of CS, PKU · XJTU +3

Policy Learning Action Chunking Robot Imitation Learning Long-Horizon Robotic Manipulation Hierarchical RL

Apr 7, 2026

Hierarchical Reinforcement Learning with Augmented Step-Level Transitions for LLM Agents

Large language model (LLM) agents have demonstrated strong capabilities in complex interactive decision-making tasks. However, existing LLM agents typically rely on increasingly long interaction histories, resulting in high computational cost and limited scalability. In this paper, we propose STEP-HRL, a hierarchical reinforcement learning (HRL) framework that enables step-level learning by conditioning only on single-step transitions rather than full interaction histories. STEP-HRL structures tasks hierarchically, using completed subtasks to represent global progress of overall task. By introducing a local progress module, it also iteratively and selectively summarizes interaction history within each subtask to produce a compact summary of local progress. Together, these components yield augmented step-level transitions for both high-level and low-level policies. Experimental results on ScienceWorld and ALFWorld benchmarks consistently demonstrate that STEP-HRL substantially outperforms baselines in terms of performance and generalization while reducing token usage. Our code is available at https://github.com/TonyStark042/STEP-HRL.

Shuai Zhen, Yanhua Yu, Ruopei Guo +2

Beijing University of Posts and Telecommunications · China Mobile Group Design Institute Co., Ltd · Singapore Management University

RL for LLM Agents Reinforcement Learning Hierarchical RL Long-Horizon LLM Agents Memory-Augmented Language Model Agents

Apr 6, 2026

Learning to Focus: CSI-Free Hierarchical MARL for Reconfigurable Reflectors

Reconfigurable Intelligent Surfaces (RIS) have the potential to engineer smart radio environments for next-generation millimeter-wave (mmWave) networks. However, the prohibitive computational overhead of Channel State Information (CSI) estimation and the dimensionality explosion inherent in centralized optimization severely hinder practical large-scale deployments. To overcome these bottlenecks, we introduce a per-element CSI-free paradigm powered by a Hierarchical Multi-Agent Reinforcement Learning (HMARL) architecture to control mechanically reconfigurable reflective surfaces. By substituting pilot-based channel estimation for each element of the device with accessible user localization data, our framework leverages spatial intelligence for macro-scale wave propagation management. The control problem is decomposed into a two-tier neural architecture: a high-level controller executes temporally extended, discrete user-to-reflector allocations, while low-level controllers autonomously optimize continuous focal points using Multi-Agent Proximal Policy Optimization (MAPPO) under a Centralized Training with Decentralized Execution (CTDE) scheme. Comprehensive deterministic ray-tracing evaluations in an indoor mmWave scenario demonstrate that this hierarchical framework achieves received signal strength indicator (RSSI) improvements of up to 7.79 dB over centralized Proximal Policy Optimization (PPO) baselines. Furthermore, the system maintains resilient beam-focusing performance under practical sub-meter localization tracking errors for up to four users and two reflector arrays. By eliminating execution-time CSI overhead while preserving high-fidelity signal redirection, this work provides a scalable and cost-effective step toward intelligent indoor wireless environments.

Hieu Le, Mostafa Ibrahim, Oguz Bedir +2

Electrical and Computer Engineering Texas A&M University College Station, Texas, USA · Engineering Technology and Industrial Distribution Texas A&M University College Station, Texas, USA · School of Performance, Visualization, and Fine Arts Texas A&M University College Station, Texas, USA

Reconfigurable Intelligent Surfaces Hierarchical RL Wireless Communications Wireless Resource Allocation Multi-Agent Reinforcement Learning

Apr 1, 2026

DISCO-TAB: A Hierarchical Reinforcement Learning Framework for Privacy-Preserving Synthesis of Complex Clinical Data

The development of robust clinical decision support systems is frequently impeded by the scarcity of high-fidelity, privacy-preserving biomedical data. While Generative Large Language Models (LLMs) offer a promising avenue for synthetic data generation, they often struggle to capture the complex, non-linear dependencies and severe class imbalances inherent in Electronic Health Records (EHR), leading to statistically plausible but clinically invalid records. To bridge this gap, we introduce DISCO-TAB (DIScriminator-guided COntrol for TABular synthesis), a novel framework that orchestrates a fine-tuned LLM with a multi-objective discriminator system optimized via Reinforcement Learning. Unlike prior methods relying on scalar feedback, DISCO-TAB evaluates synthesis at four granularities, token, sentence, feature, and row, while integrating Automated Constraint Discovery and Inverse-Frequency Reward Shaping to autonomously preserve latent medical logic and resolve minority-class collapse. We rigorously validate our framework across diverse benchmarks, including high-dimensional, small-sample medical datasets (e.g., Heart Failure, Parkinson's). Our results demonstrate that hierarchical feedback yields state-of-the-art performance, achieving up to 38.2% improvement in downstream clinical classifier utility compared to GAN and Diffusion baselines, while ensuring exceptional statistical fidelity (JSD < 0.01) and robust resistance to membership inference attacks. This work establishes a new standard for generating trustworthy, utility-preserving synthetic tabular data for sensitive healthcare applications.

Arshia Ilaty, Hossein Shirazi, Amir Rahmani +1

Computational Science Research Center, San Diego State University, San Diego, CA 92182 USA. · School of Nursing and Department of Computer Science, University of California, Irvine, CA 92697 USA. · Fowler College of Business, San Diego State University, San Diego, CA 92182 USA. +1

Synthetic Tabular Data Generation Privacy-Preserving ML Electronic Health Records Hierarchical RL

Mar 31, 2026

Hierarchical Apprenticeship Learning from Imperfect Demonstrations with Evolving Rewards

While apprenticeship learning has shown promise for inducing effective pedagogical policies directly from student interactions in e-learning environments, most existing approaches rely on optimal or near-optimal expert demonstrations under a fixed reward. Real-world student interactions, however, are often inherently imperfect and evolving: students explore, make errors, revise strategies, and refine their goals as understanding develops. In this work, we argue that imperfect student demonstrations are not noise to be discarded, but structured signals-provided their relative quality is ranked. We introduce HALIDE, Hierarchical Apprenticeship Learning from Imperfect Demonstrations with Evolving Rewards, which not only leverages sub-optimal student demonstrations, but ranks them within a hierarchical learning framework. HALIDE models student behavior at multiple levels of abstraction, enabling inference of higher-level intent and strategy from suboptimal actions while explicitly capturing the temporal evolution of student reward functions. By integrating demonstration quality into hierarchical reward inference,HALIDE distinguishes transient errors from suboptimal strategies and meaningful progress toward higher-level learning goals. Our results show that HALIDE more accurately predicts student pedagogical decisions than approaches that rely on optimal trajectories, fixed rewards, or unranked imperfect demonstrations.

Md Mirajul Islam, Rajesh Debnath, Adittya Soukarjya Saha +1

North Carolina State University, Raleigh, NC 27606, USA

Learning from Suboptimal Demonstrations Learning from Demonstration Reinforcement Learning Intelligent Tutoring Systems Hierarchical RL

Mar 19, 2026

Optimizing Resource-Constrained Non-Pharmaceutical Interventions for Multi-Cluster Outbreak Control Using Hierarchical Reinforcement Learning

Non-pharmaceutical interventions (NPIs), such as diagnostic testing and quarantine, are crucial for controlling infectious disease outbreaks but are often constrained by limited resources, particularly in early outbreak stages. In real-world public health settings, resources must be allocated across multiple outbreak clusters that emerge asynchronously, vary in size and risk, and compete for a shared resource budget. Here, a cluster corresponds to a group of close contacts generated by a single infected index case. Thus, decisions must be made under uncertainty and heterogeneous demands, while respecting operational constraints. We formulate this problem as a constrained restless multi-armed bandit and propose a hierarchical reinforcement learning framework. A global controller learns a continuous action cost multiplier that adjusts global resource demand, while a generalized local policy estimates the marginal value of allocating resources to individuals within each cluster. We evaluate the proposed framework in a realistic agent-based simulator of SARS-CoV-2 with dynamically arriving clusters. Across a wide range of system scales and testing budgets, our method consistently outperforms RMAB-inspired and heuristic baselines, improving outbreak control effectiveness by 20%-30%. Experiments on up to 40 concurrently active clusters further demonstrate that the hierarchical framework is highly scalable and enables faster decision-making than the RMAB-inspired method.

Xueqiao Peng, Andrew Perrault

The Ohio State University

Healthcare Constrained RL Hierarchical RL

Mar 17, 2026

ARISE: Agent Reasoning with Intrinsic Skill Evolution in Hierarchical Reinforcement Learning

The dominant paradigm for improving mathematical reasoning in language models relies on Reinforcement Learning with verifiable rewards. Yet existing methods treat each problem instance in isolation without leveraging the reusable strategies that emerge and accumulate during training. To this end, we introduce ARISE (Agent Reasoning via Intrinsic Skill Evolution), a hierarchical reinforcement learning framework, in which a shared policy operates both to manage skills at high-level and to generate responses at low-level (denoted as a Skills Manager and a Worker, respectively). The Manager maintains a tiered skill library through a dedicated skill generation rollout that performs structured summarization of successful solution traces (after execution), while employing a policy-driven selection mechanism to retrieve relevant skills to condition future rollouts (before execution). A hierarchical reward design guides the co-evolution of reasoning ability and library quality. Experiments on two base models and seven benchmarks spanning both competition mathematics and Omni-MATH show that ARISE consistently outperforms GRPO-family algorithms and memory-augmented baselines, with particularly notable gains on out-of-distribution tasks. Ablation studies confirm that each component contributes to the observed improvements and that library quality and reasoning performance improve in tandem throughout training. Code is available at https://github.com/Skylanding/ARISE.

Yu Li, Rui Miao, Zhengling Qi +1

Department of Electrical and Computer Engineering, George Washington University · Department of Mathematical Sciences, University of Texas at Dallas · School of Business, George Washington University

RL for Language Model Reasoning LLM Mathematical Reasoning Agent Skill Learning Hierarchical RL

Mar 15, 2026

EcoFair-CH-MARL: Scalable Constrained Hierarchical Multi-Agent RL with Real-Time Emission Budgets and Fairness Guarantees

Global decarbonisation targets and tightening market pressures demand maritime logistics solutions that are simultaneously efficient, sustainable, and equitable. We introduce EcoFair-CH-MARL, a constrained hierarchical multi-agent reinforcement learning framework that unifies three innovations: (i) a primal-dual budget layer that provably bounds cumulative emissions under stochastic weather and demand; (ii) a fairness-aware reward transformer with dynamically scheduled penalties that enforces max-min cost equity across heterogeneous fleets; and (iii) a two-tier policy architecture that decouples strategic routing from real-time vessel control, enabling linear scaling in agent count. New theoretical results establish O(\sqrt{T}) regret for both constraint violations and fairness loss. Experiments on a high-fidelity maritime digital twin (16 ports, 50 vessels) driven by automatic identification system traces, plus an energy-grid case study, show up to 15% lower emissions, 12% higher through-put, and a 45% fair-cost improvement over state-of-the-art hierarchical and constrained MARL baselines. In addition, EcoFair-CH-MARL achieves stronger equity (lower Gini and higher min-max welfare) than fairness-specific MARL baselines (e.g., SOTO, FEN), and its modular design is compatible with both policy- and value-based learners. EcoFair-CH-MARL therefore advances the feasibility of large-scale, regulation-compliant, and socially responsible multi-agent coordination in safety-critical domains.

Saad Alqithami

Computer Science Department, Al-Baha University, Albaha 65779, Saudi Arabia

Constrained MARL Multi-Agent Reinforcement Learning Multi-Agent Coordination Hierarchical RL Heterogeneous MARL

Mar 10, 2026

SCALAR: Learning and Composing Skills through LLM Guided Symbolic Planning and Deep RL Grounding

LM-based agents excel when given high-level action APIs but struggle to ground language into low-level control. Prior work has LLMs generate skills or reward functions for RL, but these one-shot approaches lack feedback to correct specification errors. We introduce SCALAR, a bidirectional framework coupling LLM planning with RL through a learned skill library. The LLM proposes skills with preconditions and effects; RL trains policies for each skill and feeds back execution results to iteratively refine specifications, improving robustness to initial errors. Pivotal Trajectory Analysis corrects LLM priors by analyzing RL trajectories; Frontier Checkpointing optionally saves environment states at skill boundaries to improve sample efficiency. On Craftax, SCALAR achieves 88.2% diamond collection, a 1.9x improvement over the best baseline, and reaches the Gnomish Mines 9.1% of the time where prior methods fail entirely.

Renos Zabounidis, Yue Wu, Simon Stepputtis +4

School of Computer Science, Carnegie Mellon University · Department of Mechanical Engineering, Virginia Tech

LLM-Guided RL LLM Agent Skill Learning LLM Agent Planning LLM Planning Hierarchical RL

Mar 9, 2026

Optimizing Reinforcement Learning Training over Digital Twin Enabled Multi-fidelity Networks

In this paper, we investigate a novel digital network twin (DNT) assisted deep learning (DL) model training framework. In particular, we consider a physical network where a base station (BS) uses several antennas to serve multiple mobile users, and a DNT that is a virtual representation of the physical network. The BS must adjust its antenna tilt angles to optimize the data rates of all users. Due to user mobility, the BS may not be able to accurately track network dynamics such as wireless channels and user mobilities. Hence, a reinforcement learning (RL) approach is used to dynamically adjust the antenna tilt angles. To train the RL, we can use data collected from the physical network and the DNT. The data collected from the physical network is more accurate but incurs more communication overhead compared to the data collected from the DNT. Therefore, it is necessary to determine the ratio of data collected from the physical network and the DNT to improve the training of the RL model. We formulate this problem as an optimization problem whose goal is to jointly optimize the tilt angle adjustment policy and the data collection strategy, aiming to maximize the data rates of all users while constraining the time delay introduced by collecting data from the physical network. To solve this problem, we propose a hierarchical RL framework that integrates robust adversarial loss and proximal policy optimization (PPO). Simulation results show that our proposed method reduces the physical network data collection delay by up to 28.01% and 1x compared to a hierarchical RL that uses vanilla PPO as the first level RL, and the baseline that uses robust-RL at the first level and selects the data collection ratio randomly.

Hanzhi Yu, Hasan Farooq, Julien Forgeat +4

Department of Electrical and Computer Engineering, University of Miami, Coral Gables, FL 33146 USA · Ericsson Research, Santa Clara, CA, 95054, USA · European AI Office, European Commission, Brussels, Belgium

Hierarchical RL Digital Twins

Mar 9, 2026

Multi-level meta-reinforcement learning with skill-based curriculum

We consider problems in sequential decision making with natural multi-level structure, where sub-tasks are assembled together to accomplish complex goals. Systematically inferring and leveraging hierarchical structure has remained a longstanding challenge; we describe an efficient multi-level procedure for repeatedly compressing Markov decision processes (MDPs), wherein a parametric family of policies at one level is treated as single actions in the compressed MDPs at higher levels, while preserving the semantic meanings and structure of the original MDP, and mimicking the natural logic to address a complex MDP. Higher-level MDPs are themselves independent MDPs with less stochasticity, and may be solved using existing algorithms. As a byproduct, spatial or temporal scales may be coarsened at higher levels, making it more efficient to find long-term optimal policies. The multi-level representation delivered by this procedure decouples sub-tasks from each other and usually greatly reduces unnecessary stochasticity and the policy search space, leading to fewer iterations and computations when solving the MDPs. A second fundamental aspect of this work is that these multi-level decompositions plus the factorization of policies into embeddings (problem-specific) and skills (including higher-order functions) yield new transfer opportunities of skills across different problems and different levels. This whole process is framed within curriculum learning, wherein a teacher organizes the student agent's learning process in a way that gradually increases the difficulty of tasks and and promotes transfer across MDPs and levels within and across curricula. The consistency of this framework and its benefits can be guaranteed under mild assumptions. We demonstrate abstraction, transferability, and curriculum learning in examples, including MazeBase+, a more complex variant of the MazeBase example.

Sichen Yang, Mauro Maggioni

Johns Hopkins University · Department of Applied Mathematics & Statistics Johns Hopkins University, 3400 N. Charles Street, Baltimore, MD 21218, USA · Department of Mathematics, Department of Applied Mathematics & Statistics Johns Hopkins University, 3400 N. Charles Street, Baltimore, MD 21218, USA

Reinforcement Learning Hierarchical RL Meta-Reinforcement Learning State Abstraction Curriculum RL Multi-Task RL

Mar 9, 2026

Fibration Policy Optimization

Large language models are increasingly trained as heterogeneous systems spanning multiple domains, expert partitions, and agentic pipelines, yet prevalent proximal objectives operate at a single scale and lack a principled mechanism for coupling token-level, trajectory-level, and higher-level hierarchical stability control. To bridge this gap, we derive the Aggregational Policy Censoring Objective (APC-Obj), the first exact unconstrained reformulation of sample-based TV-TRPO, establishing that clipping-based surrogate design and trust-region optimization are dual formulations of the same problem. Building on this foundation, we develop Fiber Bundle Gating (FBG), an algebraic framework that organizes sampled RL data as a fiber bundle and decomposes ratio gating into a base-level gate on trajectory aggregates and a fiber-level gate on per-token residuals, with provable first-order agreement with the true RL objective near on-policy. From APC-Obj and FBG we derive Fibration Policy Optimization (or simply, FiberPO), a concrete objective whose Jacobian is block-diagonal over trajectories, reduces to identity at on-policy, and provides better update direction thus improving token efficiency. The compositional nature of the framework extends beyond the trajectory-token case: fibrations compose algebraically into a Fibration Gating Hierarchy (FGH) that scales the same gating mechanism to arbitrary hierarchical depth without new primitives, as demonstrated by FiberPO-Domain, a four-level instantiation with independent trust-region budgets at the domain, prompt group, trajectory, and token levels. Together, these results connect the trust-region theory, a compositional algebraic structure, and practical multi-scale stability control into a unified framework for LLM policy optimization.

Chang Li, Tshihao Tsu, Yaren Zhang +2

JD Explore Academy · Carleton University

Policy Optimization RL for Language Models RL Fine-Tuning Trust Region Policy Optimization Hierarchical RL

Mar 8, 2026

Helix: Evolutionary Reinforcement Learning for Open-Ended Scientific Problem Solving

Large language models (LLMs) with reasoning abilities have demonstrated growing promise for tackling complex scientific problems. Yet such tasks are inherently domain-specific, unbounded and open-ended, demanding exploration across vast and flexible solution spaces. Existing approaches, whether purely learning-based or reliant on carefully designed workflows, often suffer from limited exploration efficiency and poor generalization. To overcome these challenges, we present HELIX -- a Hierarchical Evolutionary reinforcement Learning framework with In-context eXperiences. HELIX introduces two key novelties: (i) a diverse yet high-quality pool of candidate solutions that broadens exploration through in-context learning, and (ii) reinforcement learning for iterative policy refinement that progressively elevates solution quality. This synergy enables the discovery of more advanced solutions. On the circle packing task, HELIX achieves state-of-the-art result with a sum of radii of 2.63598308 using only a 14B model. Across standard machine learning benchmarks, HELIX further surpasses GPT-4o with a carefully engineered pipeline, delivering an average F1 improvement of 5.95 points on the Adult and Bank Marketing datasets.

Chang Su, Zhongkai Hao, Zhizhou Zhang +4

Bosch (China) Investment Co., Ltd. · Tsinghua-Bosch Joint Center for ML, Tsinghua University · Dept. of Comp. Sci. & Techn., Tsinghua University +1

Evolutionary RL Reinforcement Learning RL for Language Models Hierarchical RL Large Language Model-Guided Scientific Discovery

Mar 7, 2026

Learning to Reflect: Hierarchical Multi-Agent Reinforcement Learning for CSI-Free mmWave Beam-Focusing

Reconfigurable Intelligent Surfaces promise to transform wireless environments, yet practical deployment is hindered by the prohibitive overhead of Channel State Information (CSI) estimation and the dimensionality explosion inherent in centralized optimization. This paper proposes a Hierarchical Multi-Agent Reinforcement Learning (HMARL) framework for the control of mechanically reconfigurable reflective surfaces in millimeter-wave (mmWave) systems. We introduce a "CSI-free" paradigm that substitutes pilot-based channel estimation with readily available user localization data. To manage the massive combinatorial action space, the proposed architecture utilizes Multi-Agent Proximal Policy Optimization (MAPPO) under a Centralized Training with Decentralized Execution (CTDE) paradigm. The proposed architecture decomposes the control problem into two abstraction levels: a high-level controller for user-to-reflector allocation and decentralized low-level controllers for low-level focal point optimization. Comprehensive ray-tracing evaluations demonstrate that the framework achieves 2.81-7.94 dB RSSI improvements over centralized baselines, with the performance advantage widening as system complexity increases. Scalability analysis reveals that the system maintains sustained efficiency, exhibiting minimal per-user performance degradation and stable total power utilization even when user density doubles. Furthermore, robustness validation confirms the framework's viability across varying reflector aperture sizes (45-99 tiles) and demonstrates graceful performance degradation under localization errors up to 0.5 m. By eliminating CSI overhead while maintaining high-fidelity beam-focusing, this work establishes HMARL as a practical solution for intelligent mmWave environments.

Hieu Le, Oguz Bedir, Mostafa Ibrahim +2

Texas A&M University

Millimeter-Wave Communications Wireless Communications Reconfigurable Intelligent Surfaces Hierarchical RL Cooperative MARL

Mar 6, 2026

Boosting deep Reinforcement Learning using pretraining with Logical Options

Deep reinforcement learning agents are often misaligned, as they over-exploit early reward signals. Recently, several symbolic approaches have addressed these challenges by encoding sparse objectives along with aligned plans. However, purely symbolic architectures are complex to scale and difficult to apply to continuous settings. Hence, we propose a hybrid approach, inspired by humans' ability to acquire new skills. We use a two-stage framework that injects symbolic structure into neural-based reinforcement learning agents without sacrificing the expressivity of deep policies. Our method, called Hybrid Hierarchical RL (H^2RL), introduces a logical option-based pretraining strategy to steer the learning policy away from short-term reward loops and toward goal-directed behavior while allowing the final policy to be refined via standard environment interaction. Empirically, we show that this approach consistently improves long-horizon decision-making and yields agents that outperform strong neural, symbolic, and neuro-symbolic baselines.

Zihan Ye, Phil Chau, Raban Emunds +5

CS Department, Technical University of Darmstadt, Germany · AIML Group · Hessian AI +2

Neuro-Symbolic RL Reinforcement Learning Hierarchical RL

Mar 6, 2026

Task-Level Decisions to Gait Level Control: A Hierarchical Policy Approach for Quadruped Navigation

Real-world quadruped navigation is constrained by a scale mismatch between high-level navigation decisions and low-level gait execution, as well as by instabilities under out-of-distribution environmental changes. Such variations challenge sim-to-real transfer and can trigger falls when policies lack explicit interfaces for adaptation. In this paper, we present a hierarchical policy architecture for quadrupedal navigation, termed Task-level Decision to Gait Control (TDGC). A low-level policy, trained with reinforcement learning in simulation, delivers gait-conditioned locomotion and maps task requirements to a compact set of controllable behavior parameters, enabling robust mode generation and smooth switching. A high-level policy makes task-centric decisions from sparse semantic or geometric terrain cues and translates them into low-level targets, forming a traceable decision pipeline without dense maps or high-resolution terrain reconstruction. Different from end-to-end approaches, our architecture provides explicit interfaces for deployment-time tuning, fault diagnosis, and policy refinement. We introduce a structured curriculum with performance-driven progression that expands environmental difficulty and disturbance ranges. Experiments show higher task success rates on mixed terrains and out-of-distribution tests.

Sijia Li, Haoyu Wang, Shenghai Yuan +2

Quadruped Robot Navigation Robot Navigation Quadruped Locomotion Terrain-Aware Robot Locomotion Hierarchical RL Sim-to-Real Transfer

Mar 5, 2026

MIRACL: A Diverse Meta-Reinforcement Learning for Multi-Objective Multi-Echelon Combinatorial Supply Chain Optimisation

Multi-objective reinforcement learning (MORL) is effective for multi-echelon combinatorial supply chain optimisation, where tasks involve high dimensionality, uncertainty, and competing objectives. However, its deployment in dynamic environments is hindered by the need for task-specific retraining and substantial computational cost. We introduce MIRACL (Meta multI-objective Reinforcement leArning with Composite Learning), a hierarchical Meta-MORL framework that allows for a few-shot generalisation across diverse tasks. MIRACL decomposes each task into structured subproblems for efficient policy adaptation and meta-learns a global policy across tasks using a Pareto-based adaptation strategy to encourage diversity in meta-training and fine-tuning. To our knowledge, this is the first integration of Meta-MORL with such mechanisms in combinatorial optimisation. Although validated in the supply chain domain, MIRACL is theoretically domain-agnostic and applicable to broader dynamic multi-objective decision-making problems. Empirical evaluations show that MIRACL outperforms conventional MORL baselines in simple to moderate tasks, achieving up to 10% higher hypervolume and 5% better expected utility. These results underscore the potential of MIRACL for robust, efficient adaptation in multi-objective problems.

Rifny Rachman, Josh Tingey, Richard Allmendinger +3

The University of Manchester, United Kingdom · Peak AI, Ltd, United Kingdom

Supply Chain Optimization Multi-Objective Reinforcement Learning Meta-Reinforcement Learning RL for Combinatorial Optimization Combinatorial Optimization Hierarchical RL

Mar 2, 2026

LLM-assisted Semantic Option Discovery for Facilitating Adaptive Deep Reinforcement Learning

Despite achieving remarkable success in complex tasks, Deep Reinforcement Learning (DRL) is still suffering from critical issues in practical applications, such as low data efficiency, lack of interpretability, and limited cross-environment transferability. However, the learned policy generating actions based on states are sensitive to the environmental changes, struggling to guarantee behavioral safety and compliance. Recent research shows that integrating Large Language Models (LLMs) with symbolic planning is promising in addressing these challenges. Inspired by this, we introduce a novel LLM-driven closed-loop framework, which enables semantic-driven skill reuse and real-time constraint monitoring by mapping natural language instructions into executable rules and semantically annotating automatically created options. The proposed approach utilizes the general knowledge of LLMs to facilitate exploration efficiency and adapt to transferable options for similar environments, and provides inherent interpretability through semantic annotations. To validate the effectiveness of this framework, we conduct experiments on two domains, Office World and Montezuma's Revenge, respectively. The results demonstrate superior performance in data efficiency, constraint compliance, and cross-task transferability.

Chang Yao, Jinghui Qin, Kebing Jin +1

Reinforcement Learning LLM-Guided RL Hierarchical RL Constrained RL

Mar 1, 2026

HiMAC: Hierarchical Macro-Micro Learning for Long-Horizon LLM Agents

Large language model (LLM) agents have recently demonstrated strong capabilities in interactive decision-making, yet they remain fundamentally limited in long-horizon tasks that require structured planning and reliable execution. Existing approaches predominantly rely on flat autoregressive policies, where high-level reasoning and low-level actions are generated within a single token sequence, leading to inefficient exploration and severe error propagation over extended trajectories. In this work, we propose HiMAC, a hierarchical agentic RL framework that explicitly decomposes long-horizon decision-making into macro-level planning and micro-level execution. HiMAC models reasoning as a structured blueprint generation process followed by goal-conditioned action execution, enabling robust long-horizon planning within LLM-based agents. To train this hierarchy efficiently, we introduce a critic-free hierarchical policy optimization paradigm that extends group-based reinforcement learning to bi-level structures through hierarchical relative advantage estimation. Furthermore, we propose an iterative co-evolution training strategy that alternates between planner exploration and executor adaptation, mitigating the non-stationarity inherent in hierarchical learning. Extensive experiments on ALFWorld, WebShop, and Sokoban demonstrate that HiMAC consistently outperforms strong prompting and reinforcement learning baselines, achieving state-of-the-art performance and substantially improved sample efficiency across both text-based and visually grounded environments. Our results show that introducing structured hierarchy, rather than increasing model scale alone, is a key factor for enabling robust long-horizon agentic intelligence.

Hongbo Jin, Rongpeng Zhu, Jiayu Ding +2

School of Electronic and Computer Engineering, Peking University

Long-Horizon LLM Agents Long-Horizon Agent Tasks Agentic RL RL for LLM Agents Long-Horizon RL Hierarchical RL

Mar 1, 2026

Intent-Context Synergy Reinforcement Learning for Autonomous UAV Decision-Making in Air Combat

Autonomous UAV infiltration in dynamic contested environments remains a significant challenge due to the partially observable nature of threats and the conflicting objectives of mission efficiency versus survivability. Traditional Reinforcement Learning (RL) approaches often suffer from myopic decision-making and struggle to balance these trade-offs in real-time. To address these limitations, this paper proposes an Intent-Context Synergy Reinforcement Learning (ICS-RL) framework. The framework introduces two core innovations: (1) An LSTM-based Intent Prediction Module that forecasts the future trajectories of hostile units, transforming the decision paradigm from reactive avoidance to proactive planning via state augmentation; (2) A Context-Analysis Synergy Mechanism that decomposes the mission into hierarchical sub-tasks (safe cruise, stealth planning, and hostile breakthrough). We design a heterogeneous ensemble of Dueling DQN agents, each specialized in a specific tactical context. A dynamic switching controller based on Max-Advantage values seamlessly integrates these agents, allowing the UAV to adaptively select the optimal policy without hard-coded rules. Extensive simulations demonstrate that ICS-RL significantly outperforms baselines (Standard DDQN) and traditional methods (PSO, Game Theory). The proposed method achieves a mission success rate of 88% and reduces the average exposure frequency to 0.24 per episode, validating its superiority in ensuring robust and stealthy penetration in high-dynamic scenarios.

Jiahao Fu, Feng Yang

National Elite Institute of Engineering,Northwestern Polytechnical University, Xi’an, Shanxi, China · School of Automation, Northwestern Polytechnical University, Xi’an, Shanxi, China

Reinforcement Learning Partially Observable RL Deep Q-Learning Hierarchical RL

Mar 1, 2026

HierKick: Hierarchical Reinforcement Learning for Vision-Guided Soccer Robot Control

Controlling soccer robots involves multi-time-scale decision-making, which requires balancing long-term tactical planning and short-term motion execution. Traditional end-to-end reinforcement learning (RL) methods face challenges in complex dynamic environments. This paper proposes HierKick, a vision-guided soccer robot control framework based on dual-frequency hierarchical RL. The framework adopts a hierarchical control architecture featuring a 5 Hz high-level policy that integrates YOLOv8 for real-time detection and selects tasks via a coach model, and a pre-trained 50 Hz low-level controller for precise joint control. Through this architecture, the framework achieves the four steps of approaching, aligning, dribbling, and kicking. Experimental results show that the success rates of this framework are 95.2% in IsaacGym, 89.8% in Mujoco, and 80% in the real world. HierKick provides an effective hierarchical paradigm for robot control in complex environments, extendable to multi-time-scale tasks, with its modular design and skill reuse offering a new path for intelligent robot control.

Yizhi Chen, Zheng Zhang, Zhanxiang Cao +7

Tongji University, Shanghai, China. · Shanghai Innovation Institute, Shanghai, China. · Shanghai Jiao Tong University, Shanghai, China. +2

Robotic Control Robotic RL Hierarchical Robot Control Hierarchical RL Vision-Based Robot Control

Feb 25, 2026

Hierarchical Lead Critic based Multi-Agent Reinforcement Learning

Cooperative Multi-Agent Reinforcement Learning (MARL) solves complex tasks that require coordination from multiple agents, but is often limited to either local (independent learning) or global (centralized learning) perspectives. In this paper, we introduce a novel sequential training scheme and MARL architecture, which learns from multiple perspectives on different hierarchy levels. We propose the Hierarchical Lead Critic (HLC) - inspired by natural emerging distributions in team structures, where following high-level objectives combines with low-level execution. HLC demonstrates that introducing multiple hierarchies, leveraging local and global perspectives, can lead to improved performance with high sample efficiency and robust policies. Experimental results conducted on cooperative, non-communicative, and partially observable MARL benchmarks demonstrate that HLC outperforms single hierarchy baselines and scales robustly with increasing amounts of agents and difficulty.

David Eckel, Henri Meeß

Fraunhofer Institute IVI, Ingolstadt, Germany

Multi-Agent Reinforcement Learning Cooperative MARL Hierarchical RL Sequential MARL

Feb 21, 2026

In-Context Planning with Latent Temporal Abstractions

Planning-based reinforcement learning for continuous control is bottlenecked by two practical issues: planning at primitive time scales leads to prohibitive branching and long horizons, while real environments are frequently partially observable and exhibit regime shifts that invalidate stationary, fully observed dynamics assumptions. We introduce I-TAP (In-Context Latent Temporal-Abstraction Planner), an offline RL framework that unifies in-context adaptation with online planning in a learned discrete temporal-abstraction space. From offline trajectories, I-TAP learns an observation-conditioned residual-quantization VAE that compresses each observation-macro-action segment into a coarse-to-fine stack of discrete residual tokens, and a temporal Transformer that autoregressively predicts these token stacks from a short recent history. The resulting sequence model acts simultaneously as a context-conditioned prior over abstract actions and a latent dynamics model. At test time, I-TAP performs Monte Carlo Tree Search directly in token space, using short histories for implicit adaptation without gradient update, and decodes selected token stacks into executable actions. Across deterministic MuJoCo, stochastic MuJoCo with per-episode latent dynamics regimes, and high-dimensional Adroit manipulation, including partially observable variants, I-TAP consistently matches or outperforms strong model-free and model-based offline baselines, demonstrating efficient and robust in-context planning under stochastic dynamics and partial observability.

Baiting Luo, Yunuo Zhang, Nathaniel S. Keplinger +3

Vanderbilt University · William & Mary

Model-Based Planning Offline RL In-Context RL Contextual RL Hierarchical RL Partially Observable RL+1

Feb 20, 2026

Toward AI Autonomous Navigation for Mechanical Thrombectomy using Hierarchical Modular Multi-agent Reinforcement Learning (HM-MARL)

Mechanical thrombectomy (MT) is typically the optimal treatment for acute ischemic stroke involving large vessel occlusions, but access is limited due to geographic and logistical barriers. Reinforcement learning (RL) shows promise in autonomous endovascular navigation, but generalization across 'long' navigation tasks remains challenging. We propose a Hierarchical Modular Multi-Agent Reinforcement Learning (HM-MARL) framework for autonomous two-device navigation in vitro, enabling efficient and generalizable navigation. HM-MARL was developed to autonomously navigate a guide catheter and guidewire from the femoral artery to the internal carotid artery (ICA). A modular multi-agent approach was used to decompose the complex navigation task into specialized subtasks, each trained using Soft Actor-Critic RL. The framework was validated in both in silico and in vitro testbeds to assess generalization and real-world feasibility. In silico, a single-vasculature model achieved 92-100% success rates on individual anatomies, while a multi-vasculature model achieved 56-80% across multiple patient anatomies. In vitro, both HM-MARL models successfully navigated 100% of trials from the femoral artery to the right common carotid artery and 80% to the right ICA but failed on the left-side vessel superhuman challenge due to the anatomy and catheter type used in navigation. This study presents the first demonstration of in vitro autonomous navigation in MT vasculature. While HM-MARL enables generalization across anatomies, the simulation-to-real transition introduces challenges. Future work will refine RL strategies using world models and validate performance on unseen in vitro data, advancing autonomous MT towards clinical translation.

Harry Robertshaw, Nikola Fischer, Lennart Karstensen +6

School of Biomedical Engineering & Imaging Sciences, Kings College London, London, UK · School of Engineering & Materials Science, Queen Mary University of London, London, UK

Robotic Endovascular Intervention Multi-Agent Reinforcement Learning Hierarchical RL

Feb 20, 2026

Hierarchical Reward Design from Language: Enhancing Alignment of Agent Behavior with Human Specifications

When training artificial intelligence (AI) to perform tasks, humans often care not only about whether a task is completed but also how it is performed. As AI agents tackle increasingly complex tasks, aligning their behavior with human-provided specifications becomes critical for responsible AI deployment. Reward design provides a direct channel for such alignment by translating human expectations into reward functions that guide reinforcement learning (RL). However, existing methods are often too limited to capture nuanced human preferences that arise in long-horizon tasks. Hence, we introduce Hierarchical Reward Design from Language (HRDL): a problem formulation that extends classical reward design to encode richer behavioral specifications for hierarchical RL agents. We further propose Language to Hierarchical Rewards (L2HR) as a solution to HRDL. Experiments show that AI agents trained with rewards designed via L2HR not only complete tasks effectively but also better adhere to human specifications. Together, HRDL and L2HR advance the research on human-aligned AI agents.

Zhiqin Qian, Ryan Diaz, Sangwon Seo +1

Rice University, Houston, TX, USA

Reward Design for RL AI Alignment Hierarchical RL

Feb 18, 2026

A Scalable Approach to Solving Simulation-Based Network Security Games

We introduce MetaDOAR, a lightweight meta-controller that augments the Double Oracle / PSRO paradigm with a learned, partition-aware filtering layer and Q-value caching to enable scalable multi-agent reinforcement learning on very large cyber-network environments. MetaDOAR learns a compact state projection from per node structural embeddings to rapidly score and select a small subset of devices (a top-k partition) on which a conventional low-level actor performs focused beam search utilizing a critic agent. Selected candidate actions are evaluated with batched critic forwards and stored in an LRU cache keyed by a quantized state projection and local action identifiers, dramatically reducing redundant critic computation while preserving decision quality via conservative k-hop cache invalidation. Empirically, MetaDOAR attains higher player payoffs than SOTA baselines on large network topologies, without significant scaling issues in terms of memory usage or training time. This contribution provide a practical, theoretically motivated path to efficient hierarchical policy learning for large-scale networked decision problems.

Michael Lanier, Yevgeniy Vorobeychik

Multi-Agent Reinforcement Learning Hierarchical RL Cybersecurity