Reinforcement Learning in Robotics

Neueste Paper

• VINE: Taming Generative Control Policies for Reinforcement Learning

  Rushuai Yang, Zhuo Han, Houlin Li, Hecheng Wang, Zhichao Wu, Rui Zhang, Zhaowei Zhang, Zihong Chen, Xiaohan Yan, Chiming Liu, Yi Chen, Wei Shan, Maoqing Yao · 14. Juli 2026

  Flow-matching policies have emerged as an effective policy parameterization for robot learning. They iteratively generate actions from noise, enabling highly expressive modeling of complex and multimodal action distributions. However, prior works observed that scaling these policies with value-gradi…

• Beyond Euclidean Clipping: Overcoming Exploration Collapse in LLM RL via Riemannian Isometric Policy Optimization

  Zhicheng Cai, Xinyuan Guo, Hanlin Wu, Mingxuan Wang, Wei-Ying Ma, Ya-Qin Zhang, Hao Zhou · 14. Juli 2026

  Reinforcement learning (RL) has become a dominant paradigm for enhancing LLMs' reasoning capabilities. However, RL algorithms with PPO-Clip are inherently limited by exploration collapse. Subsequent works remain primarily heuristic and fail to identify the essential cause of PPO-Clip's failure. This…

• Transfer Learning Across Policy Regimes in Adaptive Multi-Agent Systems

  Roberto Garrone · 14. Juli 2026

  Policy models often assume that the relationship between a policy instrument and its outcome remains stable across institutional conditions. In adaptive socio-technical systems this assumption may fail: regulatory change can alter incentives, agents can respond strategically, and the mapping from po…

• Nonparametric Bayesian Inverse Reinforcement Learning with Data-Parallel Gibbs Sampling

  Sai Anirudh Katupilla, Shreeya Dasa Lakshminath · 14. Juli 2026

  Inverse Reinforcement Learning recovers reward functions from expert demonstrations, but standard formulations assume that all demonstrations come from a single expert. When demonstrations are pooled from multiple experts with distinct preferences, parametric methods recover an averaged reward that …

• Beyond Bayesian Nash: Learning Minimax-Regret Equilibria for Adversarial Team Games under Asymmetric Information

  Naman Aggarwal, Jonathan P. How · 14. Juli 2026

  Adversarial team games (ATGs) with asymmetric information, such as adversarial path-finding, goal search, and reachability games on graphs, require strategies that are robust to hidden opponent types, such as a hidden goal flag, and to deception. Under asymmetric information, deception is seen as st…

• Robo-ValueRL: Reliable Value Estimation for Offline-to-Online Reinforcement Learning

  Wenke Xia, Pei Ren, Wenbo Yu, Yizhuo Zhang, Jifan Li, Yixue Zhang, Yinuo Zhao, Qingyang Gao, Jianlong Fu, Jian Tang, Ji-Rong Wen, Zhengping Che, Di Hu · 14. Juli 2026

  Offline-to-online reinforcement learning is promising for generalizable robotic manipulation, yet its full-stack complexity obscures reproduction and diagnosis. Within such systems, value estimation plays a central role in prioritizing heterogeneous data for policy improvement. Despite its importanc…

• EvoCUA-1.5: Online Reinforcement Learning for Multi-turn Computer-Use Agents

  Mianqiu Huang, Taofeng Xue, Chong Peng, Jinrui Ding, Sicheng Fan, Jiale Hong, Yufei Gao, Xiaocheng Zhang, Linsen Guo, Xin Yang, Dengchang Zhao, Yuchen Xie, Peng Pei, Xunliang Xie, Xipeng Qiu · 14. Juli 2026

  Computer-use agents must solve long-horizon tasks through repeated interaction with partially observable, multimodal desktop environments. Although imitation learning and offline trajectory refinement provide strong priors, static traces cannot cover the causal feedback loop of real computer use: ea…

• Generalizing Preference-based Reinforcement Learning: a Rationality Model for Incomparability

  Simone Drago, Marco Mussi, Leonardo Bianconi, Alberto Maria Metelli · 14. Juli 2026

  In this work, we study the reinforcement learning (RL) problem from pairwise trajectory comparisons provided by a human expert. We generalize preference-based RL by formalizing a novel setting in which the expert can also label trajectory pairs as incomparable, i.e., when neither trajectory dominate…

• Measure the Sim-to-Real Gap: Designing an Affordable Real-World Benchmark Platform for Reinforcement Learning in AIoT Systems

  Rongping Zhou, Omid Tavallaie, Shuaijun Chen, Albert Y. Zomaya · 14. Juli 2026

  Reinforcement learning (RL) is commonly employed to enhance the performance of autonomous systems, including the Autonomous Internet of Things (AIoT). However, the trial-and-error nature of RL, when conducted in real-world environments, is costly and hazardous in some scenarios. Consequently, the ma…

• Disentangled Unsupervised Skill Discovery for Efficient Hierarchical Reinforcement Learning

  Jiaheng Hu, Zizhao Wang, Peter Stone, Roberto Mart\'in-Mart\'in · 14. Juli 2026

  A hallmark of intelligent agents is the ability to learn reusable skills purely from unsupervised interaction with the environment. However, existing unsupervised skill discovery methods often learn entangled skills where one skill variable simultaneously influences many entities in the environment,…

• Active Offline-to-Online Reinforcement Learning

  Alper Kamil Bozkurt, Shangtong Zhang, Yuichi Motai · 14. Juli 2026

  Background: Offline reinforcement learning (RL) enables effective policies to be trained from large, previously collected datasets and subsequently improved through limited online interaction. This offline-to-online RL (O2O-RL) paradigm is particularly promising in nonstationary domains where intera…

• A Control Theory of Predictability in Latent World Models

  Hanzhe You, Yonggang Zhang, Maohao Ran, Zhiqin Yang, Zhenyuan Zhang, Wei Xue, Jun Song, Xinmei Tian, Yike Guo · 14. Juli 2026

  Latent world models are trained to predict future states in a learned representation and are then deployed inside a planner that selects actions by simulating them forward. Current practice adopts the prediction error, the single- or multi-step rollout loss on held-out data, as the training and mode…

• EvoClawBench: Can Agents Learn Reusable Skills from Their Own Runs?

  Zhiyuan Peng, Xin Yin, Chenhao Ying, Zhe Cui, Zixiang Ding, Zhenhua Liu, Jiang Wu, Yuan Luo · 14. Juli 2026

  Existing agent benchmarks primarily test task completion, tool use, or skill utility, but do not isolate whether a runtime can convert evidence from its own runs into reusable skills that improve fresh executions after authoring overhead. We introduce EvoClawBench, a benchmark for this closed-loop s…

• Training on Irrelevant States Implies Data Augmentation: Generalization in Contextual MDPs

  Max Weltevrede, Caroline Horsch, Matthijs T. J. Spaan, Wendelin B\"ohmer · 14. Juli 2026

  In the zero-shot policy transfer (ZSPT) setting for contextual Markov decision processes (CMDP), agents train on a fixed, finite set of contexts and must generalize to new ones. Recent work has demonstrated that training on additional states, even if they are irrelevant for solving the current conte…

• Route, Communicate, and Reason: Gated Routing and Adaptive Depth for Efficient Multi-Agent Reasoning

  Sudipto Ghosh, Tanmoy Chakraborty · 14. Juli 2026

  Multi-agent ensembling multiplies active parameters and inference cost without answering three basic questions: which agents to consult, how deeply a query should traverse a hierarchy of agents, and when inter-agent communication is worth its cost. We present GRADE (Gated Routing and Adaptive Depth …

• Q-Learning Lab: Teaching Reinforcement Learning Through Learner-Generated Trace Analysis

  Ekkachai Jueng · 14. Juli 2026

  Reinforcement learning is usually introduced through the Bellman update, yet the equation often remains abstract to undergraduates: they watch policy arrows converge but rarely observe how each value is computed or why an action is chosen. We present Q-Learning Lab, a single-file, browser-based, bil…

• Learning to Fine-tune Foundation Models under Resource Limitations

  Thomas Tsouparopoulos, Iordanis Koutsopoulos · 14. Juli 2026

  We study the problem of optimal continual fine-tuning for a pre-trained Foundation Model deployed at a resource-limited device. At each time slot, a new batch of training data arrives, and the controller is faced with two options: either use the data to fine-tune the model and incur a compute cost, …

• Risk-Aware General-Utility Markov Decision Processes

  Pedro P. Santos, F\'abio Vital, Alberto Sardinha, Francisco S. Melo · 13. Juli 2026

  We study general-utility Markov decision processes (GUMDPs) with risk-aware objectives. In this framework, an agent aims to optimize a risk measure of the distribution of objective values, where the objective function depends on the frequency of visitation of states induced by the agent's policy. Fi…

• Learning More from Less: Reinforcement Learning from Hindsight

  Iris Xu, Sunshine Jiang, John Marangola, Nitish Dashora, Richard Li, Thomas Liu, Zexue He, Yuheng Zhi, Alex Pentland, Pulkit Agrawal, Zhang-Wei Hong · 13. Juli 2026

  Reinforcement learning (RL) is increasingly used to post-train vision-language-action (VLA) models, but every update consumes robot rollouts that are slow and costly to collect, making sample efficiency a central concern. Manipulation tasks typically provide only sparse rewards, so a weak policy fai…

• FlowDAgger: Human-in-the-Loop Adaptation of Generative Robot Policies in Latent Space

  Michael Murray, Daphne Chen, Simran Bagaria, Dean Fortier, Tess Hellebrekers, Galen Mullins, Harshavardhan Gajarla, Oier Mees, Maya Cakmak, Andrey Kolobov · 13. Juli 2026

  Pretrained generative robot policies based on flow matching and diffusion have achieved impressive results across a wide range of manipulation tasks. Yet real-world deployments routinely expose failure modes outside the pretraining distribution. Closing these gaps typically requires large-scale data…

• Prompt-Driven Exploration

  Sunshine Jiang, John Marangola, David Zhang, Raghuram Kowdeed, Ruiyang Luo, Nitish Dashora, Richard Li, Pulkit Agrawal, Zhang-Wei Hong · 13. Juli 2026

  Exploration is essential to RL since a policy cannot improve by repeatedly sampling the behaviors it already prefers. Standard methods inject stochasticity in the action space, but such jitter only yields rollouts close to the original. Escaping a weak policy often requires global perturbations that…

• SafeExplorer: An Unbiased Policy Gradient for Reinforcement Learning with Recovery Interventions

  Elham Daneshmand, Majid Khadiv, Glen Berseth, Hsiu-Chin Lin · 13. Juli 2026

  Training reinforcement-learning agents directly on physical robots makes every fall costly, since a fall can damage the platform and cannot be undone like a simulator reset; the goal is therefore to minimize falls during training rather than trade them off against return, as constrained Markov decis…

• Shortcut Trajectory Planning for Efficient Offline Reinforcement Learning

  Guanquan Wang, Yoshimasa Tsuruoka · 13. Juli 2026

  Diffusion-based trajectory planners have shown strong performance in offline reinforcement learning, but their iterative denoising process often incurs high inference cost. Consistency-based planners reduce the number of sampling steps, yet they typically rely on a two-stage teacher--student distill…

• Mach-Mind-4-Flash Technical Report

  Foundation Model Team · 13. Juli 2026

  We present Mach-Mind-4-Flash, a 35B-parameter Mixture-of-Experts (MoE) agentic model with 3B activated parameters. Through post-training optimization alone without scaling pre-training compute, the model achieves performance on par with or surpassing that of 100B-parameter-class models. By introduci…

• Feedback Manipulation Regularization: Enabling Offline Agent Alignment for Imitation Learning

  Benjamin Poole, Minwoo Lee · 10. Juli 2026

  Reinforcement learning (RL) research has increasingly shifted focus towards alignment, ensuring agents learn behaviors adhering to human values. While human demonstrations and feedback have proven crucial for alignment, existing approaches predominantly combine these signals using multi-stage pipeli…