The sim-to-real gap, where agents trained in a simulator face significant performance degradation during testing, is a fundamental challenge in reinforcement learning. Extansive works adopt the framework of distributionally robust RL, to learn a policy that acts robustly under worst case environment shift. Within this framework, our objective is to devise algorithms that are sample efficient with interactive data collection and large state spaces. By assuming d-rectangularity of environment dynamic shift, we identify a fundamental hardness result for learning in online Markov game, and address it by adopting minimum value assumption. Then, a novel least square value iteration type algorithm, DR-CCE-LSI, with exploration bonus devised specifically for multiple agents, is proposed to find an \episilon-approximate robust Coarse Correlated Equilibrium(CCE). To obtain sample efficient learning, we find that: when the feature mapping function satisfies certain properties, our algorithm, DR-CCE-LSI, is able to achieve ε-approximate CCE with a regret bound of O{dHmin{H,1/min{σ_i}}\sqrt{K}}, where K is the number of interacting episodes, H is the horizon length, d is the feature dimension, and \simga_i represents the uncertainty level of player i. Our work introduces the first sample-efficient algorithm for this setting, matches the best result so far in single agent setting, and achieves minimax optimalsample complexity in terms of the feature dimension d. Meanwhile, we also conduct simulation study to validate the efficacy of our algorithm in learning a robust equilibrium.

Reinforcement Learning with Verifiable Rewards (RLVR) for Multimodal Large Language Models (MLLMs) is highly dependent on high-quality labeled data, which is often scarce and prone to substantial annotation noise in real-world scenarios. Existing unsupervised RLVR methods, including pure entropy minimization, can overfit to incorrect labels and limit the crucial reward ranking signal for Group-Relative Policy Optimization (GRPO). To address these challenges and enhance noise tolerance, we propose a novel two-stage, token-level entropy optimization method for RLVR. This approach dynamically guides the model from exploration to exploitation during training. In the initial exploration phase, token-level entropy maximization promotes diverse and stochastic output generation, serving as a strong regularizer that prevents premature convergence to noisy labels and ensures sufficient intra-group variation, which enables more reliable reward gradient estimation in GRPO. As training progresses, the method transitions into the exploitation phase, where token-level entropy minimization encourages the model to produce confident and deterministic outputs, thereby consolidating acquired knowledge and refining prediction accuracy. Empirically, across three MLLM backbones - Qwen2-VL-2B, Qwen2-VL-7B, and Qwen2.5-VL-3B - spanning diverse noise settings and multiple tasks, our phased strategy consistently outperforms prior approaches by unifying and enhancing external, internal, and entropy-based methods, delivering robust and superior performance across the board.

Weakly electric fish, like Gnathonemus petersii, use a remarkable electrical modality for active sensing and communication, but studying their rich electrosensing and electrocommunication behavior and associated neural activity in naturalistic settings remains experimentally challenging. Here, we present a novel biologically-inspired computational framework to study these behaviors, where recurrent neural network (RNN) based artificial agents trained via multi-agent reinforcement learning (MARL) learn to modulate their electric organ discharges (EODs) and movement patterns to collectively forage in virtual environments. Trained agents demonstrate several emergent features consistent with real fish collectives, including heavy tailed EOD interval distributions, environmental context dependent shifts in EOD interval distributions, and social interaction patterns like freeloading, where agents reduce their EOD rates while benefiting from neighboring agents' active sensing. A minimal two-fish assay further isolates the role of electro-communication, showing that access to conspecific EODs and relative dominance jointly shape foraging success. Notably, these behaviors emerge through evolution-inspired rewards for individual fitness and emergent inter-agent interactions, rather than through rewarding agents explicitly for social interactions. Our work has broad implications for the neuroethology of weakly electric fish, as well as other social, communicating animals in which extensive recordings from multiple individuals, and thus traditional data-driven modeling, are infeasible.

In this work, we propose a computationally efficient algorithm for visual policy learning that leverages differentiable simulation and first-order analytical policy gradients. Our approach decouple the rendering process from the computation graph, enabling seamless integration with existing differentiable simulation ecosystems without the need for specialized differentiable rendering software. This decoupling not only reduces computational and memory overhead but also effectively attenuates the policy gradient norm, leading to more stable and smoother optimization. We evaluate our method on standard visual control benchmarks using modern GPU-accelerated simulation. Experiments show that our approach significantly reduces wall-clock training time and consistently outperforms all baseline methods in terms of final returns. Notably, on complex tasks such as humanoid locomotion, our method achieves a $4\times$ improvement in final return, and successfully learns a humanoid running policy within 4 hours on a single GPU.

In graph-structured multi-agent reinforcement learning (MARL) adversarial tasks such as pursuit and confrontation, agents must coordinate under highly dynamic interactions, where sparse rewards hinder efficient policy learning. We propose Adaptive Regularized Multi-Agent Soft Actor-Critic (ARAC), which integrates an attention-based graph neural network (GNN) for modeling agent dependencies with an adaptive divergence regularization mechanism. The GNN enables expressive representation of spatial relations and state features in graph environments. Divergence regularization can serve as policy guidance to alleviate the sparse reward problem, but it may lead to suboptimal convergence when the reference policy itself is imperfect. The adaptive divergence regularization mechanism enables the framework to exploit reference policies for efficient exploration in the early stages, while gradually reducing reliance on them as training progresses to avoid inheriting their limitations. Experiments in pursuit and confrontation scenarios demonstrate that ARAC achieves faster convergence, higher final success rates, and stronger scalability across varying numbers of agents compared with MARL baselines, highlighting its effectiveness in complex graph-structured environments.

Lexicographic multi-objective problems, which consist of multiple conflicting subtasks with explicit priorities, are common in real-world applications. Despite the advantages of Reinforcement Learning (RL) in single tasks, extending conventional RL methods to prioritized multiple objectives remains challenging. In particular, traditional Safe RL and Multi-Objective RL (MORL) methods have difficulty enforcing priority orderings efficiently. Therefore, Lexicographic Multi-Objective RL (LMORL) methods have been developed to address these challenges. However, existing LMORL methods either rely on heuristic threshold tuning with prior knowledge or are restricted to discrete domains. To overcome these limitations, we propose Lexicographically Projected Policy Gradient RL (LPPG-RL), a novel LMORL framework which leverages sequential gradient projections to identify feasible policy update directions, thereby enabling LPPG-RL broadly compatible with all policy gradient algorithms in continuous spaces. LPPG-RL reformulates the projection step as an optimization problem, and utilizes Dykstra's projection rather than generic solvers to deliver great speedups, especially for small- to medium-scale instances. In addition, LPPG-RL introduces Subproblem Exploration (SE) to prevent gradient vanishing, accelerate convergence and enhance stability. We provide theoretical guarantees for convergence and establish a lower bound on policy improvement. Finally, through extensive experiments in a 2D navigation environment, we demonstrate the effectiveness of LPPG-RL, showing that it outperforms existing state-of-the-art continuous LMORL methods.

Federated Learning (FL) is a promising machine learning solution in large-scale IoT systems, guaranteeing load distribution and privacy. However, FL does not natively consider infrastructure efficiency, a critical concern for systems operating in resource-constrained environments. Several Reinforcement Learning (RL) based solutions offer improved client selection for FL; however, they do not consider infrastructure challenges, such as resource limitations and device churn. Furthermore, the training of RL methods is often not designed for practical application, as these approaches frequently do not consider generalizability and are not optimized for energy efficiency. To fill this gap, we propose BIPPO (Budget-aware Independent Proximal Policy Optimization), which is an energy-efficient multi-agent RL solution that improves performance. We evaluate BIPPO on two image classification tasks run in a highly budget-constrained setting, with FL clients training on non-IID data, a challenging context for vanilla FL. The improved sampler of BIPPO enables it to increase the mean accuracy compared to non-RL mechanisms, traditional PPO, and IPPO. In addition, BIPPO only consumes a negligible proportion of the budget, which stays consistent even if the number of clients increases. Overall, BIPPO delivers a performant, stable, scalable, and sustainable solution for client selection in IoT-FL.

Abstract--Dynamic modeling and control are critical for unleashing soft robots' potential, yet remain challenging due to their complex constitutive behaviors and real-world operating conditions. Bio-inspired musculoskeletal robots, which integrate rigid skeletons with soft actuators, combine high load-bearing capacity with inherent flexibility. Although actuation dynamics have been studied through experimental methods and surrogate models, accurate and effective modeling and simulation remain a significant challenge, especially for large-scale hybrid rigid-soft robots with continuously distributed mass, kinematic loops, and diverse motion modes. T o address these challenges, we propose EquiMus, an energy-equivalent dynamic modeling framework and MuJoCo-based simulation for musculoskeletal rigid-soft hybrid robots with linear elastic actuators. The equivalence and effectiveness of the proposed approach are validated and examined through both simulations and real-world experiments on a bionic robotic leg. EquiMus further demonstrates its utility for downstream tasks, including controller design and learning-based control strategies.

We study how trajectory value depends on the learning algorithm in policy-gradient control. Using Trajectory Shapley in an uncertain LQR, we find a robust negative correlation between a trajectory's information content--Persistence of Excitation (PE)--and its marginal value under vanilla REINFORCE (e.g., r 0.38). We prove a variance-mediated mechanism: (i) for fixed energy, higher PE yields lower gradient variance; (ii) near saddle regions, higher variance increases the probability of escaping poor basins and thus raises marginal contribution. When the update is stabilized (state whitening or Fisher preconditioning), this variance channel is neutralized and information content dominates, flipping the correlation positive (e.g., r +0.29). Hence, trajectory value is algorithm-relative: it emerges from the interaction between data statistics and update dynamics. Experiments on LQR validate the two-step mechanism and the flip, and show that decision-aligned scores (Leave-One-Out) complement Shapley for pruning near the full set, while Shapley remains effective for identifying high-impact (and toxic) subsets.

Reinforcement learning (RL) systems, while achieving remarkable success across various domains, are vulnerable to adversarial attacks. This is especially a concern in vision-based environments where minor manipulations of high-dimensional image inputs can easily mislead the agent's behavior. To this end, various defenses have been proposed recently, with state-of-the-art approaches achieving robust performance even under large state perturbations. However, after closer investigation, we found that the effectiveness of the current defenses is due to a fundamental weakness of the existing $l_p$ norm-constrained attacks, which can barely alter the semantics of image input even under a relatively large perturbation budget. In this work, we propose SHIFT, a novel policy-agnostic diffusion-based state perturbation attack to go beyond this limitation. Our attack is able to generate perturbed states that are semantically different from the true states while remaining realistic and history-aligned to avoid detection. Evaluations show that our attack effectively breaks existing defenses, including the most sophisticated ones, significantly outperforming existing attacks while being more perceptually stealthy. The results highlight the vulnerability of RL agents to semantics-aware adversarial perturbations, indicating the importance of developing more robust policies.