Adaptive RL
RL: Reinforcement Learning
Latest papers
12 papers2 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.
Safe reinforcement learning (RL) aims to prevent agents from taking actions that are dangerous or destructive to their environment. This is especially important for safety-critical domains, such as robotics or autonomous driving. Formal verification can be used to prove agent safety through safety constraints. However, in practice, many policies do violate safety constraints, and thus are verified to be unsafe. Since the goal is to obtain a safe policy, we would need to retrain a new policy from scratch and then verify it again until a candidate happens to pass. Both training and verification are usually not cheap, which makes this process inefficient. We introduce VESPA (rifiable ymbolic olicy daptation), a framework for targeted fine-tuning of decision tree policies. We show that using counterexamples for policy adaptation can make existing unsafe policies safe, or at least make considerable progress towards safety. Targeted fine-tuning of the existing policy on those counterexamples enables it to learn how to avoid violating safety constraints. We thus use the result of a formal verification as a training signal for fine-tuning. On CartPole, VESPA raises the mean number of verified safe steps from 63.8 to at least 92.7, reaching after two iterations what the same loop without counterexamples reaches after ten. On MountainCarContinuous, VESPA turns an unsafe policy into a safe policy in 53 of 60 runs. We conclude that counterexamples from a verifier are an effective training signal, which can be utilized to systematically improve the safety of policies. Our implementation is available at: https://anonymous.4open.science/r/VESPA-Submission/
Adaptive Memory for Online Reinforcement Learning under Sparse Model Changes
We study the discounted reinforcement learning (RL) problem in a setting where the underlying environment changes between deployments. Each deployment provides observations from a fixed MDP. The reward function and transition kernel are fixed within each deployment. Across deployments, at most an fraction of the reward and transition kernel entries may change. In this setting, learning each model to deploy from scratch may discard useful observations from past deployments, whereas pooling all past observations can bias the estimates of entries that have already changed. We then propose an algorithm that for each state and action pair, selects how much history to reuse to estimate the reward and probabilities of the next state. We start with observations from the current deployment and add earlier deployment observations one at a time, the most recent first. After each addition, we check whether a single average reward agrees with the estimates from all histories considered until that point. We apply the same check to the distribution of next states. For each estimate, we leverage the last history that passes these aforementioned checks. The optimal control policy is then computed on top of the fitted MDP. We characterize the average gap between the optimal return and the return of the learner's policies over a finite number of deployments. We demonstrate that when , with being the cardinality of the state space, our algorithm needs only the observations from the most recent deployments, and achieves a long-run average gap of at most .
AutoRL: A Multi-Agent System towards Autonomous Reinforcement Learning
Recursive self-improvement (RSI) is one of the most promising paths toward an AI singularity for superintelligence. Achieving this vision requires AI systems to undertake the full training pipeline for iterative improvement. Reinforcement learning (RL) plays an essential role in this cycle to improve model capabilities and generalization, yet automating RL remains difficult due to unstable training dynamics and the need for sustained supervision. We introduce AutoRL, a multi-agent system for automating RL training, as a cornerstone for future RSI. Different from conducting research by end-to-end complete experiments, AutoRL monitors the evolving training state and integrates process-level supervision and research into an ongoing RL training, following the practical workflow of an RL researcher. Specifically, AutoRL consists of three RL-specific agentic roles. Perceptors track training dynamics, rollouts, evaluation, and efficiency, triggering deliberation when they detect anomalies, degradation, or stagnation. Three complementary Proposers diagnose problems and refine candidate interventions through shared evidence and checks. The Orchestrator reviews their recommendation and applies approved changes through online hot updates or checkpoint-based resumption. Experiments on Qwen3 and LongCat-Flash-Lite demonstrate the superiority of AutoRL over static RL recipes and a general agent. The research records show that existing agents can handle unattended RL supervision and dynamic adjustment. The difficulty for future RSI lies in developing fundamental methods that are valuable for resource-consuming validation.
Remember Less, Adapt Longer: Bounded-State In-Context Reinforcement Learning with Recurrent Summary Memory
In-context reinforcement learning (ICRL) enables agents to adapt to new tasks without parameter updates, relying on memory to retain what they learn from experience. For agents operating continually, existing approaches using memory trade off bounded cost against access to past experience. Approaches using growing memories, such as full-history attention and accumulating summaries, incur storage and per-decision costs that increase with task length. Fixed-size memories bound storage but restrict access: sliding windows discard older steps, while recurrent networks compress even recent interactions into a hidden state. We introduce Recurrent Summary Memory (RSM), a Transformer policy that attends exactly to a short working buffer of recent interactions and carries a fixed-capacity summary of earlier experience. When the buffer fills, RSM rewrites the summary from its previous contents and the buffer, then clears the buffer, so deployment memory and per-decision cost stay in task length. On long-running partially observable tasks, frozen RSM policies sustain their adapted performance for eight times the training horizon with about 1% of full-history memory, ending ahead of every evaluated baseline while growing memories deteriorate. When the task configuration changes mid-run, RSM re-adapts better than growing and recurrent memories. Clearing the summary or blocking the policy's access to it removes its benefit, while swapping in another task's summary steers behaviour towards that task. Together, these results show that our fixed-capacity summary can sustain in-context adaptation far beyond the training horizon.
FARL: A Fully Automated Pipeline of RL Interface and Solver Design
Existing reinforcement learning (RL) largely focuses on optimizing learning algorithms within a pre-defined task formulation, while applying RL to new tasks still relies heavily on human expertise to design the learning pipeline: what an agent observes, how it is rewarded, which algorithm it uses, and how training is configured. Automating these choices is challenging because they are tightly coupled. We introduce FARL (Fully Automated Reinforcement Learning), a framework that automates RL design by jointly searching observation and reward programs, learning algorithms, and training settings. FARL uses training statistics and observed behavior to diagnose failures, propose changes, and test whether they improve learning. Its search preserves diverse candidates and the controls needed for these tests, using a staged budget to screen designs before investing in longer training. Experimental memory records each finding together with its conditions, so an unsuccessful component can be reconsidered in a different combination. Across expert-withheld and expert-available settings, FARL outperforms the evaluated automated baselines on challenging navigation, locomotion, and manipulation tasks. On Adroit Hand Relocate, FARL achieves 97.1% success at 5M training steps per policy, compared with 0% for Eureka and LiMEN and 1.0% for native Proximal Policy Optimization (PPO) under the same policy training budget.
Cross-Platform Control for Autonomous Surface Vehicles via Adaptive Reinforcement Learning
Autonomous surface vehicles vary widely in hydrodynamic and actuation characteristics, yet most controllers are designed for single-platform deployment. We present an adaptive reinforcement learning approach for trajectory tracking that enables zero-shot cross-platform deployment using a single policy. Since the deployment platform's dynamics are unknown to the policy, we address cross-platform generalization with the standard partial-observability approach of conditioning on interaction history, employing a teacher-student architecture in which a learned module infers a latent representation of the platform dynamics. The policy is trained in simulation under randomized vessel dynamics and is deployed zero-shot to two real-world platforms without any fine-tuning, despite relying on a simple analytical dynamics model rather than a high-fidelity hydrodynamic simulator. In real-world experiments on two different platforms, the adaptive policy outperforms non-adaptive learning-based baselines by up to 58% in position mean absolute error while approaching the tracking accuracy of a platform-specific tuned controller.
Multi-Granular Attention-Driven Reinforcement Learning Framework for Web Intelligent Enhancement Systems
From the past few years, web intelligent enhancement systems increasingly rely on heterogeneous and dynamic web data to deliver personalized, context-aware services. However, traditional machine learning, deep learning, and reinforcement learning models often struggle with semantic understanding, adaptability, and scalability in continuously evolving web environments. In this research, a Multi-Granular Attention-based Reinforcement Web Intelligent Enhancement System (MGAR-WIES) is proposed to address the challenges by integrating semantic graph modeling, attention mechanisms, and adaptive reinforcement learning. Initially, heterogeneous web data comprising structured, semi-structured and unstructured sources are collected and preprocessed for generating unified feature representations. These representations are transformed into a dynamic semantic graph, where entities and their relationships are modeled by using graph embeddings enhanced by attention mechanisms for capturing both local relevance and global contextual dependencies. Subsequently, an adaptive multi-agent reinforcement learning strategy leverages the attention-aware semantic states to optimize personalized web actions like content recommendation, navigation optimization, and service adaptation. Finally, the continuous online feedback is further integrated to update graph representations and learning policies in real time by ensuring sustained adaptability and performance. The proposed MGAR-WIES acheived better results in terms of accuracy (80%) when compared with existing approaches.
HARBOR: A Harness Framework for Agentic Robot Reinforcement Learning
Reinforcement learning (RL) has become a powerful paradigm for robot learning, particularly in sim-to-real settings, but its broader adoption remains limited by the engineering pipeline surrounding the algorithms. Building tasks, shaping rewards, and tuning hyperparameters require substantial expert effort, making RL workflows costly and difficult to scale. We introduce HARBOR, an agentic framework that frames robot RL automation as a harness-engineering problem: given a simulator codebase and a task specification, it automates the workflow from environment setup to policy training in simulation. HARBOR decomposes such high-level objectives into bounded stages executed by specialized agents through standardized commands, persistent artifacts, executable gates, and reusable knowledge, and scales iteration via decentralized parallel trials and experience learning across runs. We evaluate HARBOR across 6 benchmarks and 16 tasks in total, spanning manipulation, locomotion, and bimanual dexterous control. We demonstrate that HARBOR automates the simulation RL workflow end-to-end, designs rewards, tunes algorithms to match or improve over default configurations, and reduces engineering effort at practical token and wall-clock cost; the resulting policies can also be transferred to real robots.
Data Deletion Can Help in Adaptive RL
Deploying reinforcement learning policies in the real world requires adapting to time-varying environments. We study this problem in the contextual Markov Decision Process (cMDP) framework, where a family of environments is indexed by a low-dimensional context unknown at test time. The standard approach decomposes the problem: train a so-called "universal policy" which assumes knowledge of the true context, then pair it with a context estimator which approximates context using the observed trajectory. We identify a simple, counterintuitive trick that substantially improves the estimator: randomly delete a fraction of the training buffer after each round. This works because data is collected across multiple rounds using progressively better policies, and older trajectories come from a different distribution than what the estimator will face at deployment time; random deletion creates an implicit exponential decay on older data while preserving diversity without requiring any explicit identification of which samples are stale. This reduces robustness gap by 30% for MLPs and by 6% on average for recurrent networks. Strikingly, it allows a narrow MLP with 5x fewer parameters to outperform a wide MLP trained without deletion. To understand when and why deletion helps, we analyze regularized empirical risk minimization with a mismatch between the train distribution and the distribution at deployment; in this idealized setting, we prove that removing a single uniformly random training point decreases expected test loss in expectation under mild conditions. For ridge regression we make this quantitative: deletion helps when the regularization coefficient is moderate and the signal-to-noise ratio (SNR) is sufficiently low, and, crucially, this SNR threshold gives a direct measure of how large the distribution mismatch between training and deployment must be for deletion to be beneficial.
Malliavin Calculus for Counterfactual Gradient Estimation in Adaptive Inverse Reinforcement Learning
Inverse reinforcement learning (IRL) recovers the loss function of a forward learner from its observed responses. Adaptive IRL aims to reconstruct the loss function of a forward learner by passively observing its gradients as it performs reinforcement learning (RL). This paper proposes a novel passive Langevin-based algorithm that achieves adaptive IRL. The key difficulty in adaptive IRL is that the required gradients in the passive algorithm are counterfactual, that is, they are conditioned on events of probability zero under the forward learner's trajectory. Therefore, naive Monte Carlo estimators are prohibitively inefficient, and kernel smoothing, though common, suffers from slow convergence. We overcome this by employing Malliavin calculus to efficiently estimate the required counterfactual gradients. We reformulate the counterfactual conditioning as a ratio of unconditioned expectations involving Malliavin quantities, thus recovering standard estimation rates. We derive the necessary Malliavin derivatives and their adjoint Skorohod integral formulations for a general Langevin structure, and provide a concrete algorithmic approach which exploits these for counterfactual gradient estimation.
Data-Driven Exploration for a Class of Continuous-Time Indefinite Linear--Quadratic Reinforcement Learning Problems
We study reinforcement learning (RL) for a class of continuous-time stochastic linear-quadratic (LQ) control problems, where volatilities depend on both states and controls while states are scalar-valued and there are no running control rewards, the last feature also leading to the so-called indefinite LQ controls. We propose a model-free, data-driven exploration mechanism that adaptively adjusts entropy regularization by the critic and policy variance by the actor. Unlike the constant or deterministic exploration schedules employed in the existing literature, which require extensive tuning for implementations and ignore learning progress during iterations, our adaptive exploratory approach boosts learning efficiency with minimal tuning. Despite its flexibility, our method achieves a sublinear regret bound that matches the best-known model-free results for this class of LQ problems, which were previously derived only with fixed exploration schedules. Numerical experiments demonstrate that adaptive explorations accelerate convergence and improve regret performance compared to the non-adaptive model-free and model-based counterparts.
Adaptive Reinforcement Learning for Unobservable Random Delays
In standard reinforcement learning (RL) settings, the interaction between the agent and the environment is typically modeled as a Markov decision process (MDP), which assumes that the agent observes the system state instantaneously, selects an action without delay, and executes it immediately. In real-world dynamic environments, such as cyber-physical systems, this assumption often breaks down due to delays in the interaction between the agent and the system. These delays can vary stochastically over time and are typically unobservable when deciding on an action. Existing methods deal with this uncertainty conservatively by assuming a known fixed upper bound on the delay, even if the delay is often much lower. In this work, we introduce the interaction layer, a general framework that enables agents to adaptively handle unobservable and time-varying delays. Specifically, the agent generates a matrix of possible future actions, anticipating a horizon of potential delays, to handle both unpredictable delays and lost action packets sent over networks. Building on this framework, we develop a model-based algorithm, Actor-Critic with Delay Adaptation (ACDA), which dynamically adjusts to delay patterns. Our method significantly outperforms state-of-the-art approaches across a wide range of locomotion benchmark environments, including real-world measured delays.