Reinforcement Learning in Robotics

Neueste Paper

• Multi-Agent Decision-Focused Learning via Value-Aware Sequential Communication

  Benjamin Amoh, Geoffrey Parker, Wesley Marrero · 13. April 2026

  Multi-agent coordination under partial observability requires agents to share complementary private information. While recent methods optimize messages for intermediate objectives (e.g., reconstruction accuracy or mutual information), rather than decision quality, we introduce \textbf{SeqComm-DFL}, …

• WOMBET: World Model-based Experience Transfer for Robust and Sample-efficient Reinforcement Learning

  Mintae Kim, Koushil Sreenath · 13. April 2026

  Reinforcement learning (RL) in robotics is often limited by the cost and risk of data collection, motivating experience transfer from a source task to a target task. Offline-to-online RL leverages prior data but typically assumes a given fixed dataset and does not address how to generate reliable da…

• Wireless Communication Enhanced Value Decomposition for Multi-Agent Reinforcement Learning

  Diyi Hu, Bhaskar Krishnamachari · 13. April 2026

  Cooperation in multi-agent reinforcement learning (MARL) benefits from inter-agent communication, yet most approaches assume idealized channels and existing value decomposition methods ignore who successfully shared information with whom. We propose CLOVER, a cooperative MARL framework whose central…

• Truncated Rectified Flow Policy for Reinforcement Learning with One-Step Sampling

  Xubin Zhou, Yipeng Yang, Zhan Li · 13. April 2026

  Maximum entropy reinforcement learning (MaxEnt RL) has become a standard framework for sequential decision making, yet its standard Gaussian policy parameterization is inherently unimodal, limiting its ability to model complex multimodal action distributions. This limitation has motivated increasing…

• SafeAdapt: Provably Safe Policy Updates in Deep Reinforcement Learning

  Maksim Anisimov (Imperial College London), Francesco Belardinelli (Imperial College London), Matthew Wicker (Imperial College London) · 13. April 2026

  Safety guarantees are a prerequisite to the deployment of reinforcement learning (RL) agents in safety-critical tasks. Often, deployment environments exhibit non-stationary dynamics or are subject to changing performance goals, requiring updates to the learned policy. This leads to a fundamental cha…

• StructRL: Recovering Dynamic Programming Structure from Learning Dynamics in Distributional Reinforcement Learning

  Ivo Nowak · 13. April 2026

  Reinforcement learning is typically treated as a uniform, data-driven optimization process, where updates are guided by rewards and temporal-difference errors without explicitly exploiting global structure. In contrast, dynamic programming methods rely on structured information propagation, enabling…

• You've Got a Golden Ticket: Improving Generative Robot Policies With A Single Noise Vector

  Omkar Patil, Ondrej Biza, Thomas Weng, Karl Schmeckpeper, Wil Thomason, Xiaohan Zhang, Robin Walters, Nakul Gopalan, Sebastian Castro, Eric Rosen · 13. April 2026

  What happens when a pretrained generative robot policy is provided a constant initial noise as input, rather than repeatedly sampling it from a Gaussian? We demonstrate that the performance of a pretrained, frozen diffusion or flow matching policy can be improved with respect to a downstream reward …

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

  Zhiqiang Dong, Teng Pang, Rongjian Xu, Guoqiang Wu · 13. April 2026

  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 challengi…

• Skip-Connected Policy Optimization for Implicit Advantage

  Fengwei Teng, Jinyi Bai, Xinhao Yao, Demi Ruohan Wang, Jiahao Zhao, Zhijiang Guo · 13. April 2026

  Group Relative Policy Optimization (GRPO) has proven effective in RLVR by using outcome-based rewards. While fine-grained dense rewards can theoretically improve performance, we reveal that under practical sampling budgets, Monte Carlo estimation yields high-variance and sign-inconsistent advantages…

• Distributionally Robust Token Optimization in RLHF

  Yeping Jin, Jiaming Hu, Ioannis Ch. Paschalidis · 13. April 2026

  Large Language Models (LLMs) tend to respond correctly to prompts that align to the data they were trained and fine-tuned on. Yet, small shifts in wording, format, or language can trigger surprisingly large failures, especially on multi-step reasoning problems. To address this problem, we propose a …

• Group-Aware Coordination Graph for Multi-Agent Reinforcement Learning

  Wei Duan, Jie Lu, Junyu Xuan · 13. April 2026

  Cooperative Multi-Agent Reinforcement Learning (MARL) necessitates seamless collaboration among agents, often represented by an underlying relation graph. Existing methods for learning this graph primarily focus on agent-pair relations, neglecting higher-order relationships. While several approaches…

• Inferring Latent Temporal Sparse Coordination Graph for Multi-Agent Reinforcement Learning

  Wei Duan, Jie Lu, Junyu Xuan · 13. April 2026

  Effective agent coordination is crucial in cooperative Multi-Agent Reinforcement Learning (MARL). While agent cooperation can be represented by graph structures, prevailing graph learning methods in MARL are limited. They rely solely on one-step observations, neglecting crucial historical experience…

• Advantage-Guided Diffusion for Model-Based Reinforcement Learning

  Daniele Foffano, Arvid Eriksson, David Broman, Karl H. Johansson, Alexandre Proutiere · 13. April 2026

  Model-based reinforcement learning (MBRL) with autoregressive world models suffers from compounding errors, whereas diffusion world models mitigate this by generating trajectory segments jointly. However, existing diffusion guides are either policy-only, discarding value information, or reward-based…

• AgentCE-Bench: Agent Configurable Evaluation with Scalable Horizons and Controllable Difficulty under Lightweight Environments

  Wang Yang, Chaoda Song, Xinpeng Li, Debargha Ganguly, Chuang Ma, Shouren Wang, Zhihao Dou, Yuli Zhou, Vipin Chaudhary, Xiaotian Han · 13. April 2026

  Existing Agent benchmarks suffer from two critical limitations: high environment interaction overhead (up to 41\% of total evaluation time) and imbalanced task horizon and difficulty distributions that make aggregate scores unreliable. To address these issues, we propose AgentCE-Bench built around a…

• AEROS: A Single-Agent Operating Architecture with Embodied Capability Modules

  Xue Qin, Simin Luan, Cong Yang, Zhijun Li · 10. April 2026

  Robotic systems lack a principled abstraction for organizing intelligence, capabilities, and execution in a unified manner. Existing approaches either couple skills within monolithic architectures or decompose functionality into loosely coordinated modules or multiple agents, often without a coheren…

• Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability

  Qihan Ren, Peng Wang, Ruikun Cai, Shuai Shao, Dadi Guo, Yuejin Xie, Yafu Li, Quanshi Zhang, Xia Hu, Jing Shao, Dongrui Liu · 10. April 2026

  A prevailing narrative in LLM post-training holds that supervised finetuning (SFT) memorizes while reinforcement learning (RL) generalizes. We revisit this claim for reasoning SFT with long chain-of-thought (CoT) supervision and find that cross-domain generalization is not absent but conditional, jo…

• KD-MARL: Resource-Aware Knowledge Distillation in Multi-Agent Reinforcement Learning

  Monirul Islam Pavel, Siyi Hu, Muhammad Anwar Masum, Mahardhika Pratama, Ryszard Kowalczyk, Zehong Jimmy Cao · 10. April 2026

  Real world deployment of multi agent reinforcement learning MARL systems is fundamentally constrained by limited compute memory and inference time. While expert policies achieve high performance they rely on costly decision cycles and large scale models that are impractical for edge devices or embed…

• Reason in Chains, Learn in Trees: Self-Rectification and Grafting for Multi-turn Agent Policy Optimization

  Yu Li, Sizhe Tang, Tian Lan · 9. April 2026

  Reinforcement learning for Large Language Model agents is often hindered by sparse rewards in multi-step reasoning tasks. Existing approaches like Group Relative Policy Optimization treat sampled trajectories as independent chains, assigning uniform credit to all steps in each chain and ignoring the…

• Predictive Representations for Skill Transfer in Reinforcement Learning

  Ruben Vereecken, Luke Dickens, Alessandra Russo · 9. April 2026

  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-inde…

• Information as Structural Alignment: A Dynamical Theory of Continual Learning

  Radu Negulescu · 9. April 2026

  Catastrophic forgetting is not an engineering failure. It is a mathematical consequence of storing knowledge as global parameter superposition. Existing methods, such as regularization, replay, and frozen subnetworks, add external mechanisms to a shared-parameter substrate. None derives retention fr…

• Discrete Flow Matching Policy Optimization

  Maojiang Su, Po-Chung Hsieh, Weimin Wu, Mingcheng Lu, Jiunhau Chen, Jerry Yao-Chieh Hu, Han Liu · 9. April 2026

  We introduce Discrete flow Matching policy Optimization (DoMinO), a unified framework for Reinforcement Learning (RL) fine-tuning Discrete Flow Matching (DFM) models under a broad class of policy gradient methods. Our key idea is to view the DFM sampling procedure as a multi-step Markov Decision Pro…

• Epistemic Robust Offline Reinforcement Learning

  Abhilash Reddy Chenreddy, Erick Delage · 9. April 2026

  Offline reinforcement learning learns policies from fixed datasets without further environment interaction. A key challenge in this setting is epistemic uncertainty, arising from limited or biased data coverage, particularly when the behavior policy systematically avoids certain actions. This can le…

• RAGEN-2: Reasoning Collapse in Agentic RL

  Zihan Wang, Chi Gui, Xing Jin, Qineng Wang, Licheng Liu, Kangrui Wang, Shiqi Chen, Linjie Li, Zhengyuan Yang, Pingyue Zhang, Yiping Lu, Jiajun Wu, Li Fei-Fei, Lijuan Wang, Yejin Choi, Manling Li · 9. April 2026

  RL training of multi-turn LLM agents is inherently unstable, and reasoning quality directly determines task performance. Entropy is widely used to track reasoning stability. However, entropy only measures diversity within the same input, and cannot tell whether reasoning actually responds to differe…

• Contraction-Aligned Analysis of Soft Bellman Residual Minimization with Weighted Lp-Norm for Markov Decision Problem

  Hyukjun Yang, Han-Dong Lim, Donghwan Lee · 9. April 2026

  The problem of solving Markov decision processes under function approximation remains a fundamental challenge, even under linear function approximation settings. A key difficulty arises from a geometric mismatch: while the Bellman optimality operator is contractive in the Linfty-norm, commonly used …

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

  Yong Si, Mingfei Lu, Jing Li, Yang Hu, Guijiang Li, Yueheng Song, Zhaokui Wang · 9. April 2026

  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,…