Multi-Task RL

Scaling reinforcement learning (RL) to diverse multitask settings remains a central challenge. While recent advances in model-based RL achieve strong performance, they rely on planning and complex training pipelines, making it unclear which components are essential for scalability. We revisit this question and argue that the primary driver of scalable multitask RL is not model-based control, but \emph{representation learning}. In particular, we show that combining predictive, model-based representations with high-capacity value function approximation is sufficient to achieve strong performance, even without planning. We evaluate a simple model-free algorithm, MR.Q, coupled with auxiliary predictive objectives into a scalable actor-critic architecture. This approach outperforms a recent world-model-based method and a range of deep RL baselines across a diverse suite of multitask continuous control tasks, while significantly reducing computational overhead and improving wall-clock efficiency. We observe consistent improvements with increased model capacity and show through ablations that predictive representation learning is critical for performance.

Future wireless networks demand rapid adaptation to highly heterogeneous environments and dynamic task configurations, necessitating a shift from conventional rule-based and optimization-driven radio resource management (RRM) toward artificial intelligence (AI)-driven RRM. AI-driven approaches can learn complex nonlinear relationships, generalize across diverse network conditions and enable real-time, scalable and autonomous decision-making. Among RRM techniques, coordinated multipoint (CoMP) transmission is pivotal for mitigating inter-cell interference and enhancing cell-edge performance, thereby improving quality of experience (QoE) in dense deployments. However, optimal multi-cell selection remains a complex combinatorial challenge as it requires jointly optimizing over many possible serving-cell combinations under dynamic traffic and channel conditions. Despite their success, conventional deep reinforcement learning (DRL) methods such as proximal policy optimization (PPO) suffer from poor sample efficiency, limited generalization, and costly retraining when state and action spaces change. To address these bottlenecks, we propose a Prompt Decision Transformer (PromptDT) based multi-task learning framework capable of learning across diverse network configurations and reformulating multi-cell selection as a sequence modeling problem. By leveraging offline trajectories and task-specific prompts, PromptDT enables scalable learning across diverse network configurations, including varying base stations and user equipment counts, and scheduler policies. Experimental results demonstrate that PromptDT improves QoE by up to 49% in multi-task settings compared to baselines, with performance scaling positively alongside model capacity. Moreover, PromptDT generalizes effectively to unseen tasks, achieving robust few-shot adaptation to new network configurations without retraining or fine-tuning.

GPU-parallel simulation provides abundant robot interaction, but existing benchmarks rarely combine this scale with heterogeneous manipulation tasks and standardized multi-task RL evaluation. We introduce Hebero (Heterogeneous Benchmark for Robot Learning), a GPU-parallel Isaac Lab benchmark that enables efficient joint training and evaluation of a single policy across all 40 heterogeneous tasks. Scaling experiments show that increasing parallel replicas per task improves success under a fixed wall-clock budget. To support learning with sparse rewards and limited demonstrations, we propose Demonstration-Guided Policy Optimization (DGPO), which reuses demonstrations for dense tracking rewards and asymmetric value learning. Its shared stack supports controlled comparisons of learner-specific demonstration interfaces within PPO. Within DGPO framework, we introduce IW-ABC, which uses a lightweight per-task learning progress signal to coordinate adaptive behavior cloning (ABC), relaxing demonstration guidance with task progress, and importance weighting (IW), emphasizing lagging tasks in PPO updates. With 50 demonstrations per task, IW-ABC achieves 90.1% state-input mean success, outperforming the strongest baseline FAMO-ABC by 7.8 percentage points. Its visual counterpart reaches 93.5% mean success. Real-world experiments further demonstrate that a single multi-task policy trained in simulation can successfully perform four tasks on a physical Piper robot. The project page is available at https://hebero-rl.github.io/.

Reinforcement learning (RL) post-training improves large language models (LLMs) on individual domains such as mathematical reasoning, code generation, question answering, and creative writing (CW), but training on one domain often degrades performance on others. Existing explanations based on catastrophic forgetting or global gradient conflict are incomplete: substantial interference can occur even when full-model gradients are nearly orthogonal. We show that single-domain RL produces sparse, small-magnitude parameter edits with weak overlap among top-changed neurons, while different domains still share substantial active computation routes on which update directions determine whether they act synergistically or conflict. Guided by this observation, we prove under a local perturbation model of multi-domain RL that later-domain training harms an earlier domain mainly through a second-order damage term, which under the observed sparse route structure concentrates in a low-dimensional shared conflict subspace. Moreover, a short domain refresh contracts the harmful component on this subspace, enabling selective recovery with limited collateral damage. Consistent with the theory, a brief Re-Math refresh after Code $\rightarrow$ Math $\rightarrow$ QA $\rightarrow$ CW recovers Math from 57.66 to 66.04 while largely preserving performance on the other domains, yielding the best average score of 66.39. Beyond refresh, a training-free rollback on a sparse proxy conflict coordinate set for the Math-QA pair partially restores Math, providing direct proxy-level evidence for localized damage. These results provide a localized mechanistic account of interference and recovery in multi-domain RL.

Reinforcement learning (RL) with verifiable rewards has achieved strong progress in reasoning-oriented LLMs, but extending it to multi-domain RL remains challenging due to reward unreliability in non-verifiable tasks and capability interference across domains. We propose CARE-RL to combine protocol-aware reward generation with capability-aware optimization for mitigating cross-domain conflicts. For non-verifiable tasks, the Protocol-Aware Generative Reward Model (PA-GRM) constructs prompt-level evaluation protocols and schemas before producing trace-conditioned rewards, enabling task-adaptive yet comparable evaluation of open-ended responses. For multi-domain optimization, Direction-Aware Capability Subspace Projection (DACSP) extracts historical capability directions from previous RL stages and modulates later updates by amplifying aligned components, suppressing conflicting components, and preserving orthogonal updates. Experiments across math, chat, and instruction-following benchmarks show that CARE-RL consistently outperforms standard multi-domain RL baselines, achieving Total Avg scores of 47.9 and 50.7 on Qwen2.5-7B and Qwen3-4B, respectively.

Reinforcement learning with verifiable rewards (RLVR) has become central to post-training reasoning models, yet a key limitation of existing studies is their narrow view of the reasoning space: difficulty is treated as reasoning depth alone, and reward is concentrated on forward deductive state tracking. We instead characterize the reasoning space along two dimensions. Difficulty. Beyond reasoning depth, we study environment complexity, where models must identify the correct path amid distractors and interacting structures. Rewarded reasoning form. We consider four abilities core to real-world reasoning: deductive state tracking, abductive recovery of hidden events or facts, inductive rule induction, and analogical transfer. To disentangle these factors, we construct a synthetic knowledge-graph environment with controlled pre- and post-training distributions, where each instance varies along depth, complexity, and task family. Three findings emerge: joint depth-complexity coverage outperforms single-axis recipes; reasoning families respond non-uniformly, with abductive reasoning degrading outside the RL-covered region and task correlations clustering into deductive-abductive and inductive-analogy pairs; and uniform mixing outperforms staged curricula under a fixed budget. We also find that recent off-the-shelf models exhibit the same deductive-over-abductive asymmetry, suggesting that this gap is not merely an artifact of our controlled setup.

We present a Multi-task Soft Actor-Critic (SAC) Reinforcement Learning framework designed for open-system quantum control across diverse Hamiltonians, which learns optimal pulse sequences while simultaneously discovering problem-specific evolution time T and number of control pulse segments N. Experimental results across 51 Hamiltonian variations demonstrate that the multi-task SAC model is able to generate control pulses that can drive a system, under environment noise, from its initial state to its target state with high fidelities, establishing essential foundations for universal quantum control applicable to realistic noisy quantum devices. Through progressive expansion of the training Hamiltonian set, we investigate if a single multi-task model trained using a given number of sample Hamiltonians can successfully accomplish state-transfer tasks for Hamiltonians drawn from the same Hamiltonian space but not encountered during training. In addition, our Robustness Infidelity Measure (RIM) analysis reveals that SAC trained policies exhibit superior robustness to pulse amplitude perturbations and decoherence rate variations compared to GRAPE-optimized controls.

Post-training via Reinforcement Learning (RL) has enabled Large Reasoning Models (LRMs) to achieve strong performance in individual domain. However, real-world applications increasingly require general-purpose reasoners rendering strong performance across diverse domains. Mixed-domain post-training aims to achieve this goal by jointly training with mixed domain data, but this often induces capability compromise and degradation among different domains. Existing methods attribute this performance degradation to harmful cross-domain interactions and propose various strategies to mitigate them, but these strategies may also impede beneficial knowledge sharing across domains and in turn fail to match or surpass single-domain performance. To address this problem, we propose \textbf{M}ulti-domain \textbf{C}ontrastive \textbf{P}olicy \textbf{O}ptimization (MCPO), which uses contrastive learning to utilize both positive and negative cross-domain interactions for knowledge sharing and competition. Specifically, we partition each rollout generated by LRMs according to its underlying reasoning structures and use reasoning segments to capture these structures. We thus formulate positive and negative pairs of reasoning segments as mutually augmented examples, which provide supportive and competing signals for knowledge sharing. Subsequently, we design complementary contrastive objectives for cross-domain knowledge sharing and intra-domain knowledge consolidation, targeting compatibility across domains and discriminability within each domain to form a harmonious reasoning space. Experimental results across a broad range of domains show that MCPO alleviates performance degradation caused by mixed-domain training and outperforms single-domain training in most cases.

We present GoLongRL, a fully open-source, capability-oriented post-training recipe for long-context reinforcement learning with verifiable rewards (RLVR). Existing long-context RL methods often treat data construction as a matter of designing increasingly complex retrieval paths, leading to homogeneous task coverage and reward formulations that inadequately reflect practical long-context requirements. Our work offers two contributions. (1) Capability-oriented data construction with full open release. We openly release a dataset of 23K RLVR samples, the complete construction pipeline, and all training code. Guided by a taxonomy of long-context capabilities, the dataset spans 9 task types, each paired with its natural evaluation metric. It comprises curated open-source samples from established corpora and synthetic samples whose QA pairs are generated from real source documents such as books, academic papers, and multi-turn dialogues. Under the same vanilla GRPO setup, our dataset alone outperforms the closed-source QwenLong-L1.5 dataset. Moreover, our Qwen3-30B-A3B model trained on this data delivers long-context performance comparable to DeepSeek-R1-0528 and Qwen3-235B-A22B-Thinking-2507, suggesting that broader coverage and greater reward diversity substantially benefit long-context capability improvement. (2) TMN-Reweight for heterogeneous multitask optimization. To address optimization challenges from heterogeneous rewards, we propose TMN-Reweight, which combines task-level mean normalization for cross-task reward scale alignment with difficulty-adaptive weighting for more reliable advantage estimation. TMN-Reweight further improves average performance over vanilla GRPO, with general capabilities preserved or improved across reported evaluations.

Recent progress in Reinforcement Learning (RL) provides a principled approach to optimizing Vision-Language-Action (VLA) models, facilitating a shift from trajectory imitation to active learning in the task environment. Despite improvements in control precision, most RL optimizers remain task-specific, which reduces VLA models from generalist controllers to policies that overfit to a narrow set of tasks. In this study, we conduct an in-depth analysis of this phenomenon and highlight the importance of cross-task feature representations for improving the generalizability of VLA models. Motivated by this finding, we introduce DyGRO-VLA, a two-stage optimization framework that 1) effectively captures cross-task latent representations based on information-theoretic principles, and 2) dynamically refines policy optimization via a mixture-of-RL-residuals. DyGRO-VLA enables the RL optimizer to exploit task-relevant latent information while strategically mitigating adverse interference on the learned representations throughout the optimization process. We evaluate our approach on LIBERO, RoboTwin2 benchmarks, and further validate it on real world, demonstrating consistent improvements over strong baselines under multi-task training and distribution shift.

Multi-task reinforcement learning (MTRL) aims to train a single agent to efficiently optimize performance across multiple tasks simultaneously. However, jointly optimizing all tasks often yields imbalanced learning: agents quickly solve easy tasks but learn slowly on harder ones. While prior work primarily attributes this imbalance to conflicting task gradients and proposes gradient manipulation or specialized architectures to address it, we instead focus on a distinct and under-explored challenge: imbalanced data allocation. Standard MTRL allocates an equal number of environment interactions to each task, which over-allocates data to easy tasks that require relatively few interactions to solve and under-allocates data to hard tasks that require substantially more experience to solve. To address this challenge, we introduce Distributionally Robust Adaptive Task Sampling (DRATS), an algorithm that adaptively prioritizes sampling tasks furthest from being solved. We derive DRATS by formalizing MTRL as a feasibility problem from which we derive a minimax objective for minimizing the worst-case return gap, the difference between a desired target return and the agent's return on a task. In benchmarks like MetaWorld-MT10 and MT50, DRATS improves data efficiency and increases worst-task performance compared to existing task sampling algorithms.

Complex reinforcement learning environments frequently employ multi-task and mixed-reward formulations. In these settings, heterogeneous reward distributions and correlated reward dimensions often destabilize the construction of scalar advantages. To address these challenges, we propose Reward-Decorrelated Policy Optimization (RDPO), a reward-processing method designed to explicitly target both failure modes. RDPO first utilizes Magnitude-Aware Quantile normalization to stabilize prompt-level advantage allocation across binary, fractional, and continuous rewards. It then applies Mahalanobis whitening within each active reward subspace to mitigate correlation redundancy prior to aggregation. When applied during the post-training of LongCat-Flash, RDPO enhances instruction following, writing quality, and robustness to hard prompts while remaining broadly competitive on reasoning and coding evaluations.

Soft Actor-Critic (SAC) and its variants dominate Multi-Task Reinforcement Learning (MTRL) due to their off-policy sample efficiency, while on-policy methods such as Proximal Policy Optimization (PPO) remain underexplored. We diagnose that PPO in MTRL suffers from a previously overlooked issue: critic-side gradient ill-conditioning, which may cause tail tasks to stall while easy tasks dominate the value function's updates. To address this, we propose TOPPO (Tail-Optimized PPO), a reformulation of PPO via Critic Balancing -- a set of modules that improve gradient conditioning and balance learning dynamics across tasks. Unlike prior approaches that rely on modular architectures or large models, TOPPO targets the optimization bottleneck within PPO itself. Empirically, TOPPO achieves stronger mean and tail-task performance than published SAC-family and ARS-family baselines while using substantially fewer parameters and environment steps on Meta-World+ benchmark. Notably, TOPPO matches or surpasses strong SAC baselines early in training and maintains superior performance at full budget. Ablations confirm the effectiveness of each module in TOPPO and provide insights into their interactions. Our results demonstrate that, with proper optimization, on-policy methods can rival or exceed off-policy approaches in MTRL, challenging the prevailing reliance on SAC and highlighting critic-side gradient conditioning as the central bottleneck.

Reinforcement Learning from Verifiable Rewards (RLVR) has significantly improved the reasoning capabilities of large language models (LLMs), particularly in multi-turn agentic settings involving environment interaction like tool use. However, fine-tuning such models remains prohibitively expensive due to high computational requirements, limiting accessibility. We propose MARLaaS (Multi-tenant Asynchronous RL as a Service), a system for concurrent RL fine-tuning across multiple users and tasks. Our approach is based on two key ideas: (1) sharing a base model across tenants using lightweight LoRA adapters, and (2) a disaggregated asynchronous architecture that decouples rollout generation, environment interaction, and policy training into independently scheduled stages. This design enables tasks to progress through the RL pipeline at their own pace in an event-driven manner, reducing cross-task interference, idle time, and end-to-end latency. In multi-task settings (we report up to 32 concurrent tasks), MARLaaS achieves single-task state-of-the-art performance while improving accelerator utilization by up to 4.3x and reducing end-to-end training time by 85%.

Reinforcement learning (RL) with verifiable rewards has proven effective at post-training LLMs for coding, yet deploying separate task-specific specialists incurs costs that scale with the number of tasks, motivating a unified multi-task RL (MTRL) approach. However, existing MTRL methods treat all coding tasks uniformly, relying on fixed data curricula under a shared optimization strategy, ultimately limiting the effectiveness of multi-task training. To address these limitations, we propose ASTOR, a multi-tASk code reinforcement learning framework via uTility-driven coORdination. Centered on task utility, a signal capturing each task learning potential and cross-task synergy, ASTOR comprises two coupled modules: 1) Hierarchical Utility-Routed Data Scheduling module hierarchically allocates training budget and prioritizes informative prompts, steering training toward the most valuable data and 2) Adaptive Utility-Calibrated Policy Optimization module dynamically scales per-task KL regularization, matching update constraints to each tasks current training state. Experiments on two widely-used LLMs across four representative coding tasks demonstrate that ASTOR consistently improves a single model across all tasks, outperforming the best task-specific specialist by 9.0%-9.5% and surpassing the strongest MTRL baseline by 7.5%-12.8%.

Offline zero-shot reinforcement learning (RL) aims to learn agents that optimize unseen reward functions without additional environment interaction. The standard approach to this problem trains task-conditioned policies by sampling task vectors that define linear reward functions over learned state representations. In most existing algorithms, these task vectors are randomly sampled, implicitly assuming this adequately captures the structure of the task space. We argue that doing so leads to suboptimal zero-shot generalization. To address this limitation, we propose extracting task vectors directly from the offline dataset and using them to define the task distribution used for policy training. We introduce a simple and general reward function extraction procedure that integrates into existing offline zero-shot RL algorithms. Across multiple benchmark environments and baselines, our approach improves zero-shot performance by an average of 20%, highlighting the importance of principled task sampling in offline zero-shot RL.

Over the past few decades, machine learning has been widely used to learn complex tasks. Reinforcement Learning (RL), inspired by human behavior, is a great example, as it involves developing specific behaviours for specific tasks. To further challenge algorithms, Multi-Task RL (MTRL) environments have been introduced, requiring a single model to learn multiple behaviors. The Tangled Program Graph (TPG) algorithm is a Genetic Programming (GP) algorithm designed for discrete MTRL environments. Recently, the MAPLE algorithm has been proposed, as another GP algorithm that achieves high results in single task continuous RL environments. A variation of the TPG is proposed alongside MAPLE, named Multi-Action TPG (MATPG) that aggregates MAPLE agents, and creates a control flow to activate them. Initially tested on single task RL environments only, MATPG achieved similar results to MAPLE. In this work, we present a new benchmark based on the MuJoCo Half Cheetah from Gymnasium. This benchmark features five distinct obstacles that are randomly positioned in front of the agent, each of which demands a unique behavior. This benchmark serves as a use case for MATPG, to prove its ability as a GP solution for continuous MTRL environments. Our experiments demonstrate its superiority in this multi-task use case when combined with lexicase selection. Furthermore, we examine the interpretability of the evolved graph, revealing that the decision flow of the model is fully interpretable.

Autonomous underwater vehicles are required to perform multiple tasks adaptively and in an explainable manner under dynamic, uncertain conditions and limited sensing, challenges that classical controllers struggle to address. This demands robust, generalizable, and inherently interpretable control policies for reliable long-term monitoring. Reinforcement learning, particularly multi-task RL, overcomes these limitations by leveraging shared representations to enable efficient adaptation across tasks and environments. However, while such policies show promising results in simulation and controlled experiments, they yet remain opaque and offer limited insight into the agent's internal decision-making, creating gaps in transparency, trust, and safety that hinder real-world deployment. The internal policy structure and task-specific specialization remain poorly understood. To address these gaps, we analyze the internal structure of a pretrained multi-task reinforcement learning network in the HoloOcean simulator for underwater navigation by identifying and comparing task-specific subnetworks responsible for navigating toward different species. We find that in a contextual multi-task reinforcement learning setting with related tasks, the network uses only about 1.5% of its weights to differentiate between tasks. Of these, approximately 85% connect the context-variable nodes in the input layer to the next hidden layer, highlighting the importance of context variables in such settings. Our approach provides insights into shared and specialized network components, useful for efficient model editing, transfer learning, and continual learning for underwater monitoring through a contextual multi-task reinforcement learning method.

Humanoid robots have demonstrated impressive motor skills in a wide range of tasks, yet whole-body control for humanlike long-time, dynamic fighting remains particularly challenging due to the stringent requirements on agility and stability. While imitation learning enables robots to execute human-like fighting skills, existing approaches often rely on switching among multiple single-skill policies or employing a general policy to imitate input reference motions. These strategies suffer from instability when transitioning between skills, as the mismatch of initial and terminal states across skills or reference motions introduces out-of-domain disturbances, resulting in unsmooth or unstable behaviors. In this work, we propose RPG, a hybrid expert policy framework, for smooth and stable humanoid multi-skills transition. Our approach incorporates motion transition randomization and temporal randomization to train a unified policy that generates agile fighting actions with stability and smoothness during skill transitions. Furthermore, we design a control pipeline that integrates walking/running locomotion with fighting skills, allowing humanlike long-time combat of arbitrary duration that can be seamlessly interrupted or transit action policies at any time. Extensive experiments in simulation demonstrate the effectiveness of the proposed framework, and real-world deployment on the Unitree G1 humanoid robot further validates its robustness and applicability.

Developing bipedal football robots in dynamiccombat environments presents challenges related to motionstability and deep coupling of multiple tasks, as well ascontrol switching issues between different states such as up-right walking and fall recovery. To address these problems,this paper proposes a modular reinforcement learning (RL)framework for achieving adaptive multi-task control. Firstly,this framework combines an open-loop feedforward oscilla-tor with a reinforcement learning-based feedback residualstrategy, effectively separating the generation of basic gaitsfrom complex football actions. Secondly, a posture-driven statemachine is introduced, clearly switching between the ballseeking and kicking network (BSKN) and the fall recoverynetwork (FRN), fundamentally preventing state interference.The FRN is efficiently trained through a progressive forceattenuation curriculum learning strategy. The architecture wasverified in Unity simulations of bipedal robots, demonstratingexcellent spatial adaptability-reliably finding and kicking theball even in restricted corner scenarios-and rapid autonomousfall recovery (with an average recovery time of 0.715 seconds).This ensures seamless and stable operation in complex multi-task environments.

Reinforcement Learning with Verifiable Rewards (RLVR) plays a key role in stimulating the explicit reasoning capability of Large Language Models (LLMs). We can achieve expert-level performance in some specific domains via RLVR, such as coding or math. When a general multi-domain expert-level model is required, we need to carefully consider the collaboration of RLVR across different domains. The current state-of-the-art models mainly employ two different training paradigms for multi-domain RLVR: mixed multi-task RLVR and separate RLVR followed by model merging. However, most of the works did not provide a detailed comparison and analysis about these paradigms. To this end, we choose multiple commonly used high-level tasks (e.g., math, coding, science, instruction following, and agent) as our target domains and design extensive qualitative and quantitative experiments using open-source datasets. We find the RLVR across domains exhibits small mutual interferences, and reasoning-intensive domains have mutually synergistic effects. Furthermore, we analyze the internal mechanisms from the perspectives of information constraints, model prediction behavior and self-verification. Our homepage is at https://github.com/Mosi-AI/M2RL.

Linear temporal logic (LTL) has emerged as a powerful formalism for specifying structured, temporally extended tasks in multi-task reinforcement learning (RL). However, while existing approaches in LTL-guided multi-task RL demonstrate success in simple environments, they suffer from challenges in representation learning and exploration efficiency when applied to high-dimensional environments with parameterized specifications. We present PlatoLTL, which elevates state-of-the-art methods to address both challenges. We model atomic propositions as instances of atomic predicates and inject task parameters directly into the goal embedding to enable efficient generalization. We also leverage simple priors on closeness to predicate satisfaction to enable and accelerate learning of complex tasks without biasing the optimal policy. We validate our approach on challenging environments including robotic manipulation and multi-drone navigation.

Reinforcement learning (RL) has demonstrated remarkable capabilities in training agents to solve complex tasks autonomously, such as mobile robots, UAVs/UGVs, and game-playing agents). However, scaling RL to master multiple tasks simultaneously (i.e., so-called multi-task RL) remains a significant challenge. Such a multi-task RL capability especially is important for agents to adapt to changes in real-world operational environments. State-of-the-art works show that, training agents with neural networks and shared structures across tasks promises improved generalization in simultaneous multi-task RL. However, they still suffer from task interference and incur high energy consumption due to intensive computation. To address this, we propose MTSpark, a novel methodology that enables energy-efficient simultaneous multi-task RL using spiking neural networks (SNNs) equipped with active dendrites for bio-inspired generalist agents. Specifically, MTSpark enhances a Deep Spiking Q-Network (DSQN) with active dendrites, a dueling structure, and task-specific context signals to dynamically form specialized sub-networks for individual tasks, while exploiting sparse operations for energy-efficient network processing. Experimental results demonstrate that MTSpark achieves higher performance and efficiency compared to state-of-the-art by obtaining high scores across three Atari games (i.e., Pong: -5.4, Breakout: 0.6, and Enduro: 371.2), approaching human-level performance (i.e., Pong: -3, Breakout: 31, Enduro: 368), while incurring similar memory and about 2x lower energy than state-of-the-art. These results show that our MTSpark potentially advances the frontiers toward energy-efficient generalist agents by combining RL and SNNs.

Reinforcement learning has emerged as a powerful tool for improving diffusion-based text-to-image models, but existing methods are largely limited to single-task optimization. Extending RL to multiple tasks is challenging: joint optimization suffers from cross-task interference and imbalance, while cascade RL is cumbersome and prone to catastrophic forgetting. We propose DiffusionOPD, a new multi-task training paradigm for diffusion models based on Online Policy Distillation (OPD). DiffusionOPD first trains task-specific teachers independently, then distills their capabilities into a unified student along the student own rollout trajectories. This decouples single-task exploration from multi-task integration and avoids the optimization burden of solving all tasks jointly from scratch. Theoretically, we lift the OPD framework from discrete tokens to continuous-state Markov processes, deriving a closed-form per-step KL objective that unifies both stochastic SDE and deterministic ODE refinement via mean-matching. We formally and empirically demonstrate that this analytic gradient provides lower variance and better generality compared to conventional PPO-style policy gradients. Extensive experiments show that DiffusionOPD consistently surpasses both multi-reward RL and cascade RL baselines in training efficiency and final performance, while achieving state-of-the-art results on all evaluated benchmarks.

Humanoid soccer is a challenging testbed for dynamic whole-body control, requiring robots to coordinate balance, locomotion, object interaction, and skill switching over long horizons. Existing humanoid sports methods often rely on task-specific multi-stage pipelines, making it difficult to jointly learn and compose multiple object-interactive skills within a single deployable policy. To address this, we present SkillX, a unified reinforcement learning framework that learns and composes multiple atomic soccer skills through a single command-conditioned policy. SkillX integrates three core designs: skill-specific adversarial motion priors, skill-specific critics, and an object-aware temporal encoder, enabling the robot to execute atomic skills and transition among them such as dribbling, trapping, and shooting. Experiments in simulation and on a real Noetix E1 humanoid demonstrate robust multi-skill execution, long-horizon skill composition, and successful sim-to-real deployment.