Reinforcement Learning in Robotics

Últimos artículos

• Uncertainty-Aware Rank-One MIMO Q Network Framework for Accelerated Offline Reinforcement Learning

  Thanh Nguyen, Tung Luu, Tri Ton, Sungwoong Kim, Chang D. Yoo · 24 de febrero de 2026

  Offline reinforcement learning (RL) has garnered significant interest due to its safe and easily scalable paradigm. However, training under this paradigm presents its own challenge: the extrapolation error stemming from out-of-distribution (OOD) data. Existing methodologies have endeavored to addres…

• Hilbert-Augmented Reinforcement Learning for Scalable Multi-Robot Coverage and Exploration

  Tamil Selvan Gurunathan, Aryya Gangopadhyay · 24 de febrero de 2026

  We present a coverage framework that integrates Hilbert space-filling priors into decentralized multi-robot learning and execution. We augment DQN and PPO with Hilbert-based spatial indices to structure exploration and reduce redundancy in sparse-reward environments, and we evaluate scalability in m…

• Hierarchical Reward Design from Language: Enhancing Alignment of Agent Behavior with Human Specifications

  Zhiqin Qian, Ryan Diaz, Sangwon Seo, Vaibhav Unhelkar · 24 de febrero de 2026

  When training artificial intelligence (AI) to perform tasks, humans often care not only about whether a task is completed but also how it is performed. As AI agents tackle increasingly complex tasks, aligning their behavior with human-provided specifications becomes critical for responsible AI deplo…

• Unifying Evolutionary Prompt Search and Reinforcement Learning for LLM Self-Improvement

  Lunjun Zhang, Ryan Chen, Bradly C. Stadie · 24 de febrero de 2026

  Building agentic systems that can autonomously self-improve from experience is a longstanding goal of AI. Large language models (LLMs) today primarily self-improve via two mechanisms: self-reflection for context updates, and reinforcement learning (RL) for weight updates. In this work, we propose Ev…

• Sparse Masked Attention Policies for Reliable Generalization

  Caroline Horsch, Laurens Engwegen, Max Weltevrede, Matthijs T. J. Spaan, Wendelin B\"ohmer · 24 de febrero de 2026

  In reinforcement learning, abstraction methods that remove unnecessary information from the observation are commonly used to learn policies which generalize better to unseen tasks. However, these methods often overlook a crucial weakness: the function which extracts the reduced-information represent…

• Temporal Action Representation Learning for Tactical Resource Control and Subsequent Maneuver Generation

  Hoseong Jung, Sungil Son, Daesol Cho, Jonghae Park, Changhyun Choi, H. Jin Kim · 24 de febrero de 2026

  Autonomous robotic systems should reason about resource control and its impact on subsequent maneuvers, especially when operating with limited energy budgets or restricted sensing. Learning-based control is effective in handling complex dynamics and represents the problem as a hybrid action space un…

• Stable Deep Reinforcement Learning via Isotropic Gaussian Representations

  Ali Saheb, Johan Obando-Ceron, Aaron Courville, Pouya Bashivan, Pablo Samuel Castro · 24 de febrero de 2026

  Deep reinforcement learning systems often suffer from unstable training dynamics due to non-stationarity, where learning objectives and data distributions evolve over time. We show that under non-stationary targets, isotropic Gaussian embeddings are provably advantageous. In particular, they induce …

• Descent-Guided Policy Gradient for Scalable Cooperative Multi-Agent Learning

  Shan Yang, Yang Liu · 24 de febrero de 2026

  Scaling cooperative multi-agent reinforcement learning (MARL) is fundamentally limited by cross-agent noise: when agents share a common reward, the actions of all $N$ agents jointly determine each agent's learning signal, so cross-agent noise grows with $N$. In the policy gradient setting, per-agent…

• Compositional Planning with Jumpy World Models

  Jesse Farebrother, Matteo Pirotta, Andrea Tirinzoni, Marc G. Bellemare, Alessandro Lazaric, Ahmed Touati · 24 de febrero de 2026

  The ability to plan with temporal abstractions is central to intelligent decision-making. Rather than reasoning over primitive actions, we study agents that compose pre-trained policies as temporally extended actions, enabling solutions to complex tasks that no constituent alone can solve. Such comp…

• Proximity-Based Multi-Turn Optimization: Practical Credit Assignment for LLM Agent Training

  Yangyi Fang, Jiaye Lin, Xiaoliang Fu, Cong Qin, Haolin Shi, Chang Liu, Peilin Zhao · 24 de febrero de 2026

  Multi-turn LLM agents are becoming pivotal to production systems, spanning customer service automation, e-commerce assistance, and interactive task management, where accurately distinguishing high-value informative signals from stochastic noise is critical for sample-efficient training. In real-worl…

• VariBASed: Variational Bayes-Adaptive Sequential Monte-Carlo Planning for Deep Reinforcement Learning

  Joery A. de Vries, Jinke He, Yaniv Oren, Pascal R. van der Vaart, Mathijs M. de Weerdt, Matthijs T. J. Spaan · 24 de febrero de 2026

  Optimally trading-off exploration and exploitation is the holy grail of reinforcement learning as it promises maximal data-efficiency for solving any task. Bayes-optimal agents achieve this, but obtaining the belief-state and performing planning are both typically intractable. Although deep learning…

• ISO-Bench: Can Coding Agents Optimize Real-World Inference Workloads?

  Ayush Nangia, Shikhar Mishra, Aman Gokrani, Paras Chopra · 24 de febrero de 2026

  We introduce ISO-Bench, a benchmark for coding agents to test their capabilities on real-world inference optimization tasks. These tasks were taken from vLLM and SGLang, two of the most popular LLM serving frameworks. Each task provides an agent with a codebase and bottleneck description, whereby th…

• LAD: Learning Advantage Distribution for Reasoning

  Wendi Li, Sharon Li · 24 de febrero de 2026

  Current reinforcement learning objectives for large-model reasoning primarily focus on maximizing expected rewards. This paradigm can lead to overfitting to dominant reward signals, while neglecting alternative yet valid reasoning trajectories, thereby limiting diversity and exploration. To address …

• Smooth Gate Functions for Soft Advantage Policy Optimization

  Egor Denisov, Svetlana Glazyrina, Maksim Kryzhanovskiy, Roman Ischenko · 24 de febrero de 2026

  Group Relative Policy Optimization (GRPO) has significantly advanced the training of large language models and enhanced their reasoning capabilities, while it remains susceptible to instability due to the use of hard clipping. Soft Adaptive Policy Optimization (SAPO) addresses this limitation by rep…

• In-Context Planning with Latent Temporal Abstractions

  Baiting Luo, Yunuo Zhang, Nathaniel S. Keplinger, Samir Gupta, Abhishek Dubey, Ayan Mukhopadhyay · 24 de febrero de 2026

  Planning-based reinforcement learning for continuous control is bottlenecked by two practical issues: planning at primitive time scales leads to prohibitive branching and long horizons, while real environments are frequently partially observable and exhibit regime shifts that invalidate stationary, …

• (Perlin) Noise as AI coordinator

  Kaijie Xu, Clark Verbrugge · 24 de febrero de 2026

  Large scale control of nonplayer agents is central to modern games, while production systems still struggle to balance several competing goals: locally smooth, natural behavior, and globally coordinated variety across space and time. Prior approaches rely on handcrafted rules or purely stochastic tr…

• How to Allocate, How to Learn? Dynamic Rollout Allocation and Advantage Modulation for Policy Optimization

  Yangyi Fang, Jiaye Lin, Xiaoliang Fu, Cong Qin, Haolin Shi, Chaowen Hu, Lu Pan, Ke Zeng, Xunliang Cai · 24 de febrero de 2026

  Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for Large Language Model (LLM) reasoning, yet current methods face key challenges in resource allocation and policy optimization dynamics: (i) uniform rollout allocation ignores gradient variance heterogeneity across problems…

• Polychromic Objectives for Reinforcement Learning

  Jubayer Ibn Hamid, Ifdita Hasan Orney, Ellen Xu, Chelsea Finn, Dorsa Sadigh · 24 de febrero de 2026

  Reinforcement learning fine-tuning (RLFT) is a dominant paradigm for improving pretrained policies for downstream tasks. These pretrained policies, trained on large datasets, produce generations with a broad range of promising but unrefined behaviors. Often, a critical failure mode of RLFT arises wh…

• Flow Actor-Critic for Offline Reinforcement Learning

  Jongseong Chae, Jongeui Park, Yongjae Shin, Gyeongmin Kim, Seungyul Han, Youngchul Sung · 23 de febrero de 2026

  The dataset distributions in offline reinforcement learning (RL) often exhibit complex and multi-modal distributions, necessitating expressive policies to capture such distributions beyond widely-used Gaussian policies. To handle such complex and multi-modal datasets, in this paper, we propose Flow …

• Mean-Field Reinforcement Learning without Synchrony

  Shan Yang · 23 de febrero de 2026

  Mean-field reinforcement learning (MF-RL) scales multi-agent RL to large populations by reducing each agent's dependence on others to a single summary statistic -- the mean action. However, this reduction requires every agent to act at every time step; when some agents are idle, the mean action is s…

• CAE: Repurposing the Critic as an Explorer in Deep Reinforcement Learning

  Yexin Li · 23 de febrero de 2026

  Exploration remains a fundamental challenge in reinforcement learning, as many existing methods either lack theoretical guarantees or fall short in practical effectiveness. In this paper, we propose CAE, i.e., the Critic as an Explorer, a lightweight approach that repurposes the value networks in st…

• Learning Optimal and Sample-Efficient Decision Policies with Guarantees

  Daqian Shao · 23 de febrero de 2026

  The paradigm of decision-making has been revolutionised by reinforcement learning and deep learning. Although this has led to significant progress in domains such as robotics, healthcare, and finance, the use of RL in practice is challenging, particularly when learning decision policies in high-stak…

• Nested Training for Mutual Adaptation in Human-AI Teaming

  Upasana Biswas, Durgesh Kalwar, Subbarao Kambhampati, Sarath Sreedharan · 23 de febrero de 2026

  Mutual adaptation is a central challenge in human--AI teaming, as humans naturally adjust their strategies in response to a robot's policy. Existing approaches aim to improve diversity in training partners to approximate human behavior, but these partners are static and fail to capture adaptive beha…

• MIRA: Memory-Integrated Reinforcement Learning Agent with Limited LLM Guidance

  Narjes Nourzad, Carlee Joe-Wong · 23 de febrero de 2026

  Reinforcement learning (RL) agents often suffer from high sample complexity in sparse or delayed reward settings due to limited prior structure. Large language models (LLMs) can provide subgoal decompositions, plausible trajectories, and abstract priors that facilitate early learning. However, heavy…

• Diffusing to Coordinate: Efficient Online Multi-Agent Diffusion Policies

  Zhuoran Li, Hai Zhong, Xun Wang, Qingxin Xia, Lihua Zhang, Longbo Huang · 23 de febrero de 2026

  Online Multi-Agent Reinforcement Learning (MARL) is a prominent framework for efficient agent coordination. Crucially, enhancing policy expressiveness is pivotal for achieving superior performance. Diffusion-based generative models are well-positioned to meet this demand, having demonstrated remarka…