Reinforcement Learning in Robotics

Últimos artículos

• Learning what to say and how precisely: Efficient Communication via Differentiable Discrete Communication Learning

  Aditya Kapoor, Yash Bhisikar, Benjamin Freed, Jan Peters, Mingfei Sun · 4 de noviembre de 2025

  Effective communication in multi-agent reinforcement learning (MARL) is critical for success but constrained by bandwidth, yet past approaches have been limited to complex gating mechanisms that only decide \textit{whether} to communicate, not \textit{how precisely}. Learning to optimize message pre…

• LPAC: Learnable Perception-Action-Communication Loops with Applications to Coverage Control

  Saurav Agarwal, Ramya Muthukrishnan, Walker Gosrich, Vijay Kumar, Alejandro Ribeiro · 4 de noviembre de 2025

  Coverage control is the problem of navigating a robot swarm to collaboratively monitor features or a phenomenon of interest not known a priori. The problem is challenging in decentralized settings with robots that have limited communication and sensing capabilities. We propose a learnable Perception…

• Evaluation and Optimization of Leave-one-out Cross-validation for the Lasso

  Ryan Burn · 4 de noviembre de 2025

  I develop an algorithm to produce the piecewise quadratic that computes leave-one-out cross-validation for the lasso as a function of its hyperparameter. The algorithm can be used to find exact hyperparameters that optimize leave-one-out cross-validation either globally or locally, and its practical…

• Breaking the Performance Ceiling in Reinforcement Learning requires Inference Strategies

  Felix Chalumeau, Daniel Rajaonarivonivelomanantsoa, Ruan de Kock, Claude Formanek, Sasha Abramowitz, Oumayma Mahjoub, Wiem Khlifi, Simon Du Toit, Louay Ben Nessir, Refiloe Shabe, Arnol Fokam, Siddarth Singh, Ulrich Mbou Sob, Arnu Pretorius · 4 de noviembre de 2025

  Reinforcement learning (RL) systems have countless applications, from energy-grid management to protein design. However, such real-world scenarios are often extremely difficult, combinatorial in nature, and require complex coordination between multiple agents. This level of complexity can cause even…

• SLAP: Shortcut Learning for Abstract Planning

  Y. Isabel Liu, Bowen Li, Benjamin Eysenbach, Tom Silver · 4 de noviembre de 2025

  Long-horizon decision-making with sparse rewards and continuous states and actions remains a fundamental challenge in AI and robotics. Task and motion planning (TAMP) is a model-based framework that addresses this challenge by planning hierarchically with abstract actions (options). These options ar…

• Dataset Distillation for Offline Reinforcement Learning

  Jonathan Light, Yuanzhe Liu, Ziniu Hu · 4 de noviembre de 2025

  Offline reinforcement learning often requires a quality dataset that we can train a policy on. However, in many situations, it is not possible to get such a dataset, nor is it easy to train a policy to perform well in the actual environment given the offline data. We propose using data distillation …

• Gymnasium: A Standard Interface for Reinforcement Learning Environments

  Mark Towers, Ariel Kwiatkowski, Jordan Terry, John U. Balis, Gianluca De Cola, Tristan Deleu, Manuel Goul\~ao, Andreas Kallinteris, Markus Krimmel, Arjun KG, Rodrigo Perez-Vicente, Andrea Pierr\'e, Sander Schulhoff, Jun Jet Tai, Hannah Tan, Omar G. Younis · 4 de noviembre de 2025

  Reinforcement Learning (RL) is a continuously growing field that has the potential to revolutionize many areas of artificial intelligence. However, despite its promise, RL research is often hindered by the lack of standardization in environment and algorithm implementations. This makes it difficult …

• Language-Driven Coordination and Learning in Multi-Agent Simulation Environments

  Zhengyang Li, Sawyer Campos, Nana Wang · 4 de noviembre de 2025

  This paper introduces LLM-MARL, a unified framework that incorporates large language models (LLMs) into multi-agent reinforcement learning (MARL) to enhance coordination, communication, and generalization in simulated game environments. The framework features three modular components of Coordinator,…

• Reinforcement Learning from Human Feedback

  Nathan Lambert · 4 de noviembre de 2025

  Reinforcement learning from human feedback (RLHF) has become an important technical and storytelling tool to deploy the latest machine learning systems. In this book, we hope to give a gentle introduction to the core methods for people with some level of quantitative background. The book starts with…

• Self-Harmony: Learning to Harmonize Self-Supervision and Self-Play in Test-Time Reinforcement Learning

  Ru Wang, Wei Huang, Qi Cao, Yusuke Iwasawa, Yutaka Matsuo, Jiaxian Guo · 4 de noviembre de 2025

  Test-time reinforcement learning (TTRL) offers a label-free paradigm for adapting models using only synthetic signals at inference, but its success hinges on constructing reliable learning signals. Standard approaches such as majority voting often collapse to spurious yet popular answers. We introdu…

• MARFT: Multi-Agent Reinforcement Fine-Tuning

  Junwei Liao, Muning Wen, Jun Wang, Weinan Zhang · 4 de noviembre de 2025

  LLM-based Multi-Agent Systems have demonstrated remarkable capabilities in addressing complex, agentic tasks, from generating high-quality presentation slides to even conducting sophisticated scientific research. Meanwhile, RL has been widely recognized for its effectiveness in enhancing agent intel…

• On the Fundamental Limitations of Decentralized Learnable Reward Shaping in Cooperative Multi-Agent Reinforcement Learning

  Aditya Akella · 4 de noviembre de 2025

  Recent advances in learnable reward shaping have shown promise in single-agent reinforcement learning by automatically discovering effective feedback signals. However, the effectiveness of decentralized learnable reward shaping in cooperative multi-agent settings remains poorly understood. We propos…

• Learning Intractable Multimodal Policies with Reparameterization and Diversity Regularization

  Ziqi Wang, Jiashun Liu, Ling Pan · 4 de noviembre de 2025

  Traditional continuous deep reinforcement learning (RL) algorithms employ deterministic or unimodal Gaussian actors, which cannot express complex multimodal decision distributions. This limitation can hinder their performance in diversity-critical scenarios. There have been some attempts to design o…

• KFCPO: Kronecker-Factored Approximated Constrained Policy Optimization

  Joonyoung Lim, Younghwan Yoo · 4 de noviembre de 2025

  We propose KFCPO, a novel Safe Reinforcement Learning (Safe RL) algorithm that combines scalable Kronecker-Factored Approximate Curvature (K-FAC) based second-order policy optimization with safety-aware gradient manipulation. KFCPO leverages K-FAC to perform efficient and stable natural gradient upd…

• Bootstrap Off-policy with World Model

  Guojian Zhan, Likun Wang, Xiangteng Zhang, Jiaxin Gao, Masayoshi Tomizuka, Shengbo Eben Li · 4 de noviembre de 2025

  Online planning has proven effective in reinforcement learning (RL) for improving sample efficiency and final performance. However, using planning for environment interaction inevitably introduces a divergence between the collected data and the policy's actual behaviors, degrading both model learnin…

• Improving the Robustness of Control of Chaotic Convective Flows with Domain-Informed Reinforcement Learning

  Michiel Straat, Thorben Markmann, Sebastian Peitz, Barbara Hammer · 4 de noviembre de 2025

  Chaotic convective flows arise in many real-world systems, such as microfluidic devices and chemical reactors. Stabilizing these flows is highly desirable but remains challenging, particularly in chaotic regimes where conventional control methods often fail. Reinforcement Learning (RL) has shown pro…

• Is Risk-Sensitive Reinforcement Learning Properly Resolved?

  Ruiwen Zhou, Minghuan Liu, Kan Ren, Xufang Luo, Weinan Zhang, Dongsheng Li · 4 de noviembre de 2025

  Due to the nature of risk management in learning applicable policies, risk-sensitive reinforcement learning (RSRL) has been realized as an important direction. RSRL is usually achieved by learning risk-sensitive objectives characterized by various risk measures, under the framework of distributional…

• Action Chunking and Exploratory Data Collection Yield Exponential Improvements in Behavior Cloning for Continuous Control

  Thomas T. Zhang, Daniel Pfrommer, Chaoyi Pan, Nikolai Matni, Max Simchowitz · 3 de noviembre de 2025

  This paper presents a theoretical analysis of two of the most impactful interventions in modern learning from demonstration in robotics and continuous control: the practice of action-chunking (predicting sequences of actions in open-loop) and exploratory augmentation of expert demonstrations. Though…

• Multimodal LLM-assisted Evolutionary Search for Programmatic Control Policies

  Qinglong Hu, Xialiang Tong, Mingxuan Yuan, Fei Liu, Zhichao Lu, Qingfu Zhang · 3 de noviembre de 2025

  Deep reinforcement learning has achieved impressive success in control tasks. However, its policies, represented as opaque neural networks, are often difficult for humans to understand, verify, and debug, which undermines trust and hinders real-world deployment. This work addresses this challenge by…

• Challenges in Credit Assignment for Multi-Agent Reinforcement Learning in Open Agent Systems

  Alireza Saleh Abadi, Leen-Kiat Soh · 3 de noviembre de 2025

  In the rapidly evolving field of multi-agent reinforcement learning (MARL), understanding the dynamics of open systems is crucial. Openness in MARL refers to the dynam-ic nature of agent populations, tasks, and agent types with-in a system. Specifically, there are three types of openness as reported…

• Uncertainty-Based Smooth Policy Regularisation for Reinforcement Learning with Few Demonstrations

  Yujie Zhu, Charles A. Hepburn, Matthew Thorpe, Giovanni Montana · 3 de noviembre de 2025

  In reinforcement learning with sparse rewards, demonstrations can accelerate learning, but determining when to imitate them remains challenging. We propose Smooth Policy Regularisation from Demonstrations (SPReD), a framework that addresses the fundamental question: when should an agent imitate a de…

• Think Outside the Policy: In-Context Steered Policy Optimization

  Hsiu-Yuan Huang, Chenming Tang, Weijie Liu, Saiyong Yang, Yunfang Wu · 31 de octubre de 2025

  Existing Reinforcement Learning from Verifiable Rewards (RLVR) methods, such as Group Relative Policy Optimization (GRPO), have achieved remarkable progress in improving the reasoning capabilities of Large Reasoning Models (LRMs). However, they exhibit limited exploration due to reliance on on-polic…

• Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning

  Yihe Deng, I-Hung Hsu, Jun Yan, Zifeng Wang, Rujun Han, Gufeng Zhang, Yanfei Chen, Wei Wang, Tomas Pfister, Chen-Yu Lee · 31 de octubre de 2025

  Large Language Models (LLMs) often struggle with problems that require multi-step reasoning. For small-scale open-source models, Reinforcement Learning with Verifiable Rewards (RLVR) fails when correct solutions are rarely sampled even after many attempts, while Supervised Fine-Tuning (SFT) tends to…

• Smart Exploration in Reinforcement Learning using Bounded Uncertainty Models

  J. S. van Hulst, W. P. M. H. Heemels, D. J. Antunes · 31 de octubre de 2025

  Reinforcement learning (RL) is a powerful framework for decision-making in uncertain environments, but it often requires large amounts of data to learn an optimal policy. We address this challenge by incorporating prior model knowledge to guide exploration and accelerate the learning process. Specif…

• Oryx: a Scalable Sequence Model for Many-Agent Coordination in Offline MARL

  Claude Formanek, Omayma Mahjoub, Louay Ben Nessir, Sasha Abramowitz, Ruan de Kock, Wiem Khlifi, Daniel Rajaonarivonivelomanantsoa, Simon Du Toit, Arnol Fokam, Siddarth Singh, Ulrich Mbou Sob, Felix Chalumeau, Arnu Pretorius · 31 de octubre de 2025

  A key challenge in offline multi-agent reinforcement learning (MARL) is achieving effective many-agent multi-step coordination in complex environments. In this work, we propose Oryx, a novel algorithm for offline cooperative MARL to directly address this challenge. Oryx adapts the recently proposed …