Reinforcement Learning in Robotics

Últimos artículos

• Breaking Task Impasses Quickly: Adaptive Neuro-Symbolic Learning for Open-World Robotics

  Pierrick Lorang · 27 de enero de 2026

  Adapting to unforeseen novelties in open-world environments remains a major challenge for autonomous systems. While hybrid planning and reinforcement learning (RL) approaches show promise, they often suffer from sample inefficiency, slow adaptation, and catastrophic forgetting. We present a neuro-sy…

• Embodiment-Induced Coordination Regimes in Tabular Multi-Agent Q-Learning

  Muhammad Ahmed Atif, Nehal Naeem Haji, Mohammad Shahid Shaikh, Muhammad Ebad Atif · 27 de enero de 2026

  Centralized value learning is often assumed to improve coordination and stability in multi-agent reinforcement learning, yet this assumption is rarely tested under controlled conditions. We directly evaluate it in a fully tabular predator-prey gridworld by comparing independent and centralized Q-lea…

• Online Difficulty Filtering for Reasoning Oriented Reinforcement Learning

  Sanghwan Bae, Jiwoo Hong, Min Young Lee, Hanbyul Kim, JeongYeon Nam, Donghyun Kwak · 27 de enero de 2026

  Recent advances in reinforcement learning with verifiable rewards (RLVR) show that large language models enhance their reasoning abilities when trained with verifiable signals. However, due to reward sparsity, effectiveness depends heavily on selecting samples of appropriate difficulty. In this work…

• Yunjue Agent Tech Report: A Fully Reproducible, Zero-Start In-Situ Self-Evolving Agent System for Open-Ended Tasks

  Haotian Li, Shijun Yang, Weizhen Qi, Silei Zhao, Rui Hua, Mingzhu Song, Xiaojian Yang, Chao Peng · 27 de enero de 2026

  Conventional agent systems often struggle in open-ended environments where task distributions continuously drift and external supervision is scarce. Their reliance on static toolsets or offline training lags behind these dynamics, leaving the system's capability boundaries rigid and unknown. To addr…

• ART for Diffusion Sampling: A Reinforcement Learning Approach to Timestep Schedule

  Yilie Huang, Wenpin Tang, Xunyu Zhou · 27 de enero de 2026

  We consider time discretization for score-based diffusion models to generate samples from a learned reverse-time dynamic on a finite grid. Uniform and hand-crafted grids can be suboptimal given a budget on the number of time steps. We introduce Adaptive Reparameterized Time (ART) that controls the c…

• The Landscape of Agentic Reinforcement Learning for LLMs: A Survey

  Guibin Zhang, Hejia Geng, Xiaohang Yu, Zhenfei Yin, Zaibin Zhang, Zelin Tan, Heng Zhou, Zhongzhi Li, Xiangyuan Xue, Yijiang Li, Yifan Zhou, Yang Chen, Chen Zhang, Yutao Fan, Zihu Wang, Songtao Huang, Francisco Piedrahita-Velez, Yue Liao, Hongru Wang, Mengyue Yang, Heng Ji, Jun Wang, Shuicheng Yan, Philip Torr, Lei Bai · 27 de enero de 2026

  The emergence of agentic reinforcement learning (Agentic RL) marks a paradigm shift from conventional reinforcement learning applied to large language models (LLM RL), reframing LLMs from passive sequence generators into autonomous, decision-making agents embedded in complex, dynamic worlds. This su…

• Rank-1 Approximation of Inverse Fisher for Natural Policy Gradients in Deep Reinforcement Learning

  Yingxiao Huo, Satya Prakash Dash, Radu Stoican, Samuel Kaski, Mingfei Sun · 27 de enero de 2026

  Natural gradients have long been studied in deep reinforcement learning due to their fast convergence properties and covariant weight updates. However, computing natural gradients requires inversion of the Fisher Information Matrix (FIM) at each iteration, which is computationally prohibitive in nat…

• Towards Generalisable Imitation Learning Through Conditioned Transition Estimation and Online Behaviour Alignment

  Nathan Gavenski, Matteo Leonetti, Odinaldo Rodrigues · 27 de enero de 2026

  State-of-the-art imitation learning from observation methods (ILfO) have recently made significant progress, but they still have some limitations: they need action-based supervised optimisation, assume that states have a single optimal action, and tend to apply teacher actions without full considera…

• GFlowNet Foundations

  Yoshua Bengio, Salem Lahlou, Tristan Deleu, Edward J. Hu, Mo Tiwari, Emmanuel Bengio · 27 de enero de 2026

  Generative Flow Networks (GFlowNets) have been introduced as a method to sample a diverse set of candidates in an active learning context, with a training objective that makes them approximately sample in proportion to a given reward function. In this paper, we show a number of additional theoretica…

• Learning Transferable Skills in Action RPGs via Directed Skill Graphs and Selective Adaptation

  Ali Najar · 27 de enero de 2026

  Lifelong agents should expand their competence over time without retraining from scratch or overwriting previously learned behaviors. We investigate this in a challenging real-time control setting (Dark Souls III) by representing combat as a directed skill graph and training its components in a hier…

• Towards Real-time Adaptation of Embodied Agent in Human-Robot Collaboration

  Shipeng Liu, Boshen Zhang, Zhehui Huang · 27 de enero de 2026

  Large Language Models (LLMs) have opened transformative possibilities for human-robot collaboration. However, enabling real-time collaboration requires both low latency and robust reasoning, and most LLMs suffer from high latency. To address this gap, we first propose a fine-grained benchmark that e…

• DIML: Differentiable Inverse Mechanism Learning from Behaviors of Multi-Agent Learning Trajectories

  Zhiyu An, Wan Du · 27 de enero de 2026

  We study inverse mechanism learning: recovering an unknown incentive-generating mechanism from observed strategic interaction traces of self-interested learning agents. Unlike inverse game theory and multi-agent inverse reinforcement learning, which typically infer utility/reward parameters inside a…

• Success Conditioning as Policy Improvement: The Optimization Problem Solved by Imitating Success

  Daniel Russo · 27 de enero de 2026

  A widely used technique for improving policies is success conditioning, in which one collects trajectories, identifies those that achieve a desired outcome, and updates the policy to imitate the actions taken along successful trajectories. This principle appears under many names -- rejection samplin…

• Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy Prefixes

  Amrith Setlur, Zijian Wang, Andrew Cohen, Paria Rashidinejad, Sang Michael Xie · 27 de enero de 2026

  Typical reinforcement learning (RL) methods for LLM reasoning waste compute on hard problems, where correct on-policy traces are rare, policy gradients vanish, and learning stalls. To bootstrap more efficient RL, we consider reusing old sampling FLOPs (from prior inference or RL training) in the for…

• Vision-Proprioception Fusion with Mamba2 in End-to-End Reinforcement Learning for Motion Control

  Xiaowen Tao, Yinuo Wang, Jinzhao Zhou · 27 de enero de 2026

  End-to-end reinforcement learning (RL) for motion control trains policies directly from sensor inputs to motor commands, enabling unified controllers for different robots and tasks. However, most existing methods are either blind (proprioception-only) or rely on fusion backbones with unfavorable com…

• Paying Less Generalization Tax: A Cross-Domain Generalization Study of RL Training for LLM Agents

  Zhihan Liu, Lin Guan, Yixin Nie, Kai Zhang, Zhuoqun Hao, Lin Chen, Asli Celikyilmaz, Zhaoran Wang, Na Zhang · 27 de enero de 2026

  Generalist LLM agents are often post-trained on a narrow set of environments but deployed across far broader, unseen domains. In this work, we investigate the challenge of agentic post-training when the eventual test domains are unknown. Specifically, we analyze which properties of reinforcement lea…

• Multi-Agent Deep Reinforcement Learning Under Constrained Communications

  Shahil Shaik, Jonathon M. Smereka, Yue Wang · 27 de enero de 2026

  Centralized training with decentralized execution (CTDE) has been the dominant paradigm in multi-agent reinforcement learning (MARL), but its reliance on global state information during training introduces scalability, robustness, and generalization bottlenecks. Moreover, in practical scenarios such…

• EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience

  Taofeng Xue, Chong Peng, Mianqiu Huang, Linsen Guo, Tiancheng Han, Haozhe Wang, Jianing Wang, Xiaocheng Zhang, Xin Yang, Dengchang Zhao, Jinrui Ding, Xiandi Ma, Yuchen Xie, Peng Pei, Xunliang Cai, Xipeng Qiu · 26 de enero de 2026

  The development of native computer-use agents (CUA) represents a significant leap in multimodal AI. However, their potential is currently bottlenecked by the constraints of static data scaling. Existing paradigms relying primarily on passive imitation of static datasets struggle to capture the intri…

• Distinguishing Task-Specific and General-Purpose AI in Regulation

  Jennifer Wang, Andrew Selbst, Solon Barocas, Suresh Venkatasubramanian · 26 de enero de 2026

  Over the past decade, policymakers have developed a set of regulatory tools to ensure AI development aligns with key societal goals. Many of these tools were initially developed in response to concerns with task-specific AI and therefore encode certain assumptions about the nature of AI systems and …

• Task Aware Dreamer for Task Generalization in Reinforcement Learning

  Chengyang Ying, Xinning Zhou, Zhongkai Hao, Hang Su, Songming Liu, Dong Yan, Jun Zhu · 26 de enero de 2026

  A long-standing goal of reinforcement learning is to acquire agents that can learn on training tasks and generalize well on unseen tasks that may share a similar dynamic but with different reward functions. The ability to generalize across tasks is important as it determines an agent's adaptability …

• Mixture-of-Models: Unifying Heterogeneous Agents via N-Way Self-Evaluating Deliberation

  Tims Pecerskis, Aivars Smirnovs · 26 de enero de 2026

  This paper introduces the N-Way Self-Evaluating Deliberation (NSED) protocol, a Runtime Mixture-of-Models (MoM) architecture that constructs emergent composite models from a plurality of distinct expert agents. Unlike traditional Mixture-of-Experts (MoE) which rely on static gating networks, NSED em…

• LongCat-Flash-Thinking-2601 Technical Report

  Meituan LongCat Team, Anchun Gui, Bei Li, Bingyang Tao, Bole Zhou, Borun Chen, Chao Zhang, Chao Zhang, Chen Gao, Chen Zhang, Chengcheng Han, Chenhui Yang, Chuyu Zhang, Cong Chen, Cunguang Wang, Daoru Pan, Defei Bu, Dengchang Zhao, Di Xiu, Dishan Liu, Dongyu Ru, Dunwei Tu, Fan Wu, Fengcheng Yuan, Fengcun Li, Gang Xu, Guanyu Wu, Guoyuan Lin, Haibin Wang, Hansi Yang, Hao Yang, Haonan Yan, Haoxiang Ma, Haoxing Wen, Hongyan Hao, Hongyin Tang, Hongyu Zang, Hongzhi Ni, Hui Su, Jiacheng Zhang, Jiahong Zhou, Jiahuan Li, Jiaming Wang, Jian Yang, Jianfei Zhang, Jianhao Xu, Jianing Wang, Jiapeng Zhu, Jiaqi Sun, Jiarong Shi, Jiarui Zhao, Jingang Wang, Jinluan Yang, Jinrui Ding, Jinwei Xiao, Jiyuan He, Juncan Xu, Kefeng Zhang, Keheng Wang, Li Wei, Lianhui Ma, Lin Qiu, Lingbing Kong, Lingchuan Liu, Linsen Guo, Mengshen Zhu, Mengxia Shen, Mingyang Zhu, Peiguang Li, Peng Pei, Pengcheng Jia, Pengtao Zhang, Peng Zhao, Qi Gu, Qiong Huang, Qiyuan Duan, Quanchi Weng, Rongxiang Weng, Rongzhi Zhang, Rumei Li, Shanglin Lei, Shengnan An, Shijun Dai, Shuaikang Liu, Shuang Zhou, Shuo Wang, Songyuan Zhao, Tao Liang, Tianhao Hu, Tianze Chen, Wei Liu, Wei Shi, Wei Wang, Weifeng Tang, Wenjie Shi, Wenlong Zhu, Wentao Chen, Wentao Shi, Xi Su, Xiangcheng Liu, Xiandi Ma, Xiangyu Xi, Xiangyuan Liu, Xiangzhou Huang, Xiao Liu, Xiaodong Cai, Xiaolong Chen, Xiaowei Shi, Xiaoyu Li, Xin Chen, Xingchen Liu, Xuan Huang, Xuezhi Cao, Xunliang Cai, Yan Chen, Yang Bai, Yang Liu, Yang Yang, Yang Zheng, Yaoming Wang, Yaoming Zhu, Yaqi Huo, Yanyu Chen, Yaorui Shi, Yerui Sun, Yi Zhang, Yihao Chen, Yi-Kai Zhang, Yifan Lu, Yifan Zhao, Yitao Zhai, Yongjing Yin, Yongwei Zhou, Youshao Xiao, Yuchuan Dai, Yuchen Xie, Yuchen Yu, Yufei Zhang, Yuhuai Wei, Yulei Qian, Yunfan Liang, Yunke Zhao, Yuwei Jiang, Yuxin Bian, Yuxin Chen, Yuxin Liu, Yue Xu, Yueqing Sun, Zeyang Yu, Zhao Yang, Zhengsheng Huang, Zhengyu Chen, Zhijian Liu, Zhikang Xia, Zhimin Lin, Zhiyuan Yao, Zhuofan Chen, Zhuowen Han, Zijian Zhang, Ziran Li, Ziwen Wang, Ziyuan Zhuang · 26 de enero de 2026

  We introduce LongCat-Flash-Thinking-2601, a 560-billion-parameter open-source Mixture-of-Experts (MoE) reasoning model with superior agentic reasoning capability. LongCat-Flash-Thinking-2601 achieves state-of-the-art performance among open-source models on a wide range of agentic benchmarks, includi…

• Boosting Deep Reinforcement Learning with Semantic Knowledge for Robotic Manipulators

  Luc\'ia G\"uitta-L\'opez, Vincenzo Suriani, Jaime Boal, \'Alvaro J. L\'opez-L\'opez, Daniele Nardi · 26 de enero de 2026

  Deep Reinforcement Learning (DRL) is a powerful framework for solving complex sequential decision-making problems, particularly in robotic control. However, its practical deployment is often hindered by the substantial amount of experience required for learning, which results in high computational a…

• On Computational Limits of FlowAR Models: Expressivity and Efficiency

  Yang Cao, Chengyue Gong, Yekun Ke, Xiaoyu Li, Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song · 26 de enero de 2026

  The expressive power and computational complexity of deep visual generative models, such as flow-based and autoregressive (AR) models, have gained considerable interest for their wide-ranging applications in generative tasks. However, the theoretical characterization of their expressiveness through …

• A Regularized Actor-Critic Algorithm for Bi-Level Reinforcement Learning

  Sihan Zeng, Sujay Bhatt, Sumitra Ganesh, Alec Koppel · 26 de enero de 2026

  We study a structured bi-level optimization problem where the upper-level objective is a smooth function and the lower-level problem is policy optimization in a Markov decision process (MDP). The upper-level decision variable parameterizes the reward of the lower-level MDP, and the upper-level objec…