Reinforcement Learning in Robotics

Latest papers

• Interactionless Inverse Reinforcement Learning: A Data-Centric Framework for Durable Alignment

  Elias Malomgr\'e, Pieter Simoens · 17 February 2026

  AI alignment is growing in importance, yet current approaches suffer from a critical structural flaw that entangles the safety objectives with the agent's policy. Methods such as Reinforcement Learning from Human Feedback and Direct Preference Optimization create opaque, single-use alignment artifac…

• Near-Optimal Regret for Policy Optimization in Contextual MDPs with General Offline Function Approximation

  Orin Levy, Aviv Rosenberg, Alon Cohen, Yishay Mansour · 17 February 2026

  We introduce \texttt{OPO-CMDP}, the first policy optimization algorithm for stochastic Contextual Markov Decision Process (CMDPs) under general offline function approximation. Our approach achieves a high probability regret bound of $\widetilde{O}(H^4\sqrt{T|S||A|\log(|\mathcal{F}||\mathcal{P}|)}),$…

• Scaling the Scaling Logic: Agentic Meta-Synthesis of Logic Reasoning

  Bowen Liu, Zhi Wu, Runquan Xie, Zhanhui Kang, Jia Li · 17 February 2026

  Scaling verifiable training signals remains a key bottleneck for Reinforcement Learning from Verifiable Rewards (RLVR). Logical reasoning is a natural substrate: constraints are formal and answers are programmatically checkable. However, prior synthesis pipelines either depend on expert-written code…

• Enabling Option Learning in Sparse Rewards with Hindsight Experience Replay

  Gabriel Romio, Mateus Begnini Melchiades, Bruno Castro da Silva, Gabriel de Oliveira Ramos · 17 February 2026

  Hierarchical Reinforcement Learning (HRL) frameworks like Option-Critic (OC) and Multi-updates Option Critic (MOC) have introduced significant advancements in learning reusable options. However, these methods underperform in multi-goal environments with sparse rewards, where actions must be linked t…

• WIMLE: Uncertainty-Aware World Models with IMLE for Sample-Efficient Continuous Control

  Mehran Aghabozorgi, Alireza Moazeni, Yanshu Zhang, Ke Li · 17 February 2026

  Model-based reinforcement learning promises strong sample efficiency but often underperforms in practice due to compounding model error, unimodal world models that average over multi-modal dynamics, and overconfident predictions that bias learning. We introduce WIMLE, a model-based method that exten…

• Decoupled Continuous-Time Reinforcement Learning via Hamiltonian Flow

  Minh Nguyen · 17 February 2026

  Many real-world control problems, ranging from finance to robotics, evolve in continuous time with non-uniform, event-driven decisions. Standard discrete-time reinforcement learning (RL), based on fixed-step Bellman updates, struggles in this setting: as time gaps shrink, the $Q$-function collapses …

• On the Learning Dynamics of RLVR at the Edge of Competence

  Yu Huang, Zixin Wen, Yuejie Chi, Yuting Wei, Aarti Singh, Yingbin Liang, Yuxin Chen · 17 February 2026

  Reinforcement learning with verifiable rewards (RLVR) has been a main driver of recent breakthroughs in large reasoning models. Yet it remains a mystery how rewards based solely on final outcomes can help overcome the long-horizon barrier to extended reasoning. To understand this, we develop a theor…

• BPP: Long-Context Robot Imitation Learning by Focusing on Key History Frames

  Max Sobol Mark, Jacky Liang, Maria Attarian, Chuyuan Fu, Debidatta Dwibedi, Dhruv Shah, Aviral Kumar · 17 February 2026

  Many robot tasks require attending to the history of past observations. For example, finding an item in a room requires remembering which places have already been searched. However, the best-performing robot policies typically condition only on the current observation, limiting their applicability t…

• Fluid-Agent Reinforcement Learning

  Shishir Sharma, Doina Precup, Theodore J. Perkins · 17 February 2026

  The primary focus of multi-agent reinforcement learning (MARL) has been to study interactions among a fixed number of agents embedded in an environment. However, in the real world, the number of agents is neither fixed nor known a priori. Moreover, an agent can decide to create other agents (for exa…

• RNM-TD3: N:M Semi-structured Sparse Reinforcement Learning From Scratch

  Isam Vrce, Andreas Kassler, G\"ok\c{c}e Aydos · 17 February 2026

  Sparsity is a well-studied technique for compressing deep neural networks (DNNs) without compromising performance. In deep reinforcement learning (DRL), neural networks with up to 5% of their original weights can still be trained with minimal performance loss compared to their dense counterparts. Ho…

• RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling

  Yang Liu, Jiaqi Li, Zilong Zheng · 17 February 2026

  Rule-based reasoning is acknowledged as one of the fundamental problems of reasoning. While recent studies show that large reasoning models (LRMs) have remarkable reasoning capabilities enhanced by reinforcement learning (RL), real applications still face severe challenges due to variations in rule …

• Mean Flow Policy with Instantaneous Velocity Constraint for One-step Action Generation

  Guojian Zhan, Letian Tao, Pengcheng Wang, Yixiao Wang, Yiheng Li, Yuxin Chen, Masayoshi Tomizuka, Shengbo Eben Li · 17 February 2026

  Learning expressive and efficient policy functions is a promising direction in reinforcement learning (RL). While flow-based policies have recently proven effective in modeling complex action distributions with a fast deterministic sampling process, they still face a trade-off between expressiveness…

• On-Policy Supervised Fine-Tuning for Efficient Reasoning

  Anhao Zhao, Ziyang Chen, Junlong Tong, Yingqi Fan, Fanghua Ye, Shuhao Li, Yunpu Ma, Wenjie Li, Xiaoyu Shen · 17 February 2026

  Large reasoning models (LRMs) are commonly trained with reinforcement learning (RL) to explore long chain-of-thought reasoning, achieving strong performance at high computational cost. Recent methods add multi-reward objectives to jointly optimize correctness and brevity, but these complex extension…

• Intelligence as Trajectory-Dominant Pareto Optimization

  Truong Xuan Khanh, Truong Quynh Hoa · 17 February 2026

  Despite recent advances in artificial intelligence, many systems exhibit stagnation in long-horizon adaptability despite continued performance optimization. This work argues that such limitations do not primarily arise from insufficient learning, data, or model capacity, but from a deeper structural…

• GRAIL: Goal Recognition Alignment through Imitation Learning

  Osher Elhadad, Felipe Meneguzzi, Reuth Mirsky · 17 February 2026

  Understanding an agent's goals from its behavior is fundamental to aligning AI systems with human intentions. Existing goal recognition methods typically rely on an optimal goal-oriented policy representation, which may differ from the actor's true behavior and hinder the accurate recognition of the…

• Adaptive Value Decomposition: Coordinating a Varying Number of Agents in Urban Systems

  Yexin Li, Jinjin Guo, Haoyu Zhang, Yuhan Zhao, Yiwen Sun, Zihao Jiao · 17 February 2026

  Multi-agent reinforcement learning (MARL) provides a promising paradigm for coordinating multi-agent systems (MAS). However, most existing methods rely on restrictive assumptions, such as a fixed number of agents and fully synchronous action execution. These assumptions are often violated in urban s…

• GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning

  Lakshya A Agrawal, Shangyin Tan, Dilara Soylu, Noah Ziems, Rishi Khare, Krista Opsahl-Ong, Arnav Singhvi, Herumb Shandilya, Michael J Ryan, Meng Jiang, Christopher Potts, Koushik Sen, Alexandros G. Dimakis, Ion Stoica, Dan Klein, Matei Zaharia, Omar Khattab · 17 February 2026

  Large language models (LLMs) are increasingly adapted to downstream tasks via reinforcement learning (RL) methods like Group Relative Policy Optimization (GRPO), which often require thousands of rollouts to learn new tasks. We argue that the interpretable nature of language often provides a much ric…

• When is Offline Policy Selection Sample Efficient for Reinforcement Learning?

  Vincent Liu, Prabhat Nagarajan, Andrew Patterson, Martha White · 17 February 2026

  Offline reinforcement learning algorithms often require careful hyperparameter tuning. Before deployment, we need to select amongst a set of candidate policies. However, there is limited understanding about the fundamental limits of this offline policy selection (OPS) problem. In this work we provid…

• Evolutionary System Prompt Learning can Facilitate Reinforcement Learning for LLMs

  Lunjun Zhang, Ryan Chen, Bradly C. Stadie · 17 February 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…

• World Models for Policy Refinement in StarCraft II

  Yixin Zhang, Ziyi Wang, Yiming Rong, Haoxi Wang, Jinling Jiang, Shuang Xu, Haoran Wu, Shiyu Zhou, Bo Xu · 17 February 2026

  Large Language Models (LLMs) have recently shown strong reasoning and generalization capabilities, motivating their use as decision-making policies in complex environments. StarCraft II (SC2), with its massive state-action space and partial observability, is a challenging testbed. However, existing …

• Dual Goal Representations

  Seohong Park, Deepinder Mann, Sergey Levine · 17 February 2026

  In this work, we introduce dual goal representations for goal-conditioned reinforcement learning (GCRL). A dual goal representation characterizes a state by "the set of temporal distances from all other states"; in other words, it encodes a state through its relations to every other state, measured …

• Composable Model-Free RL for Navigation with Input-Affine Systems

  Xinhuan Sang, Abdelrahman Abdelgawad, Roberto Tron · 16 February 2026

  As autonomous robots move into complex, dynamic real-world environments, they must learn to navigate safely in real time, yet anticipating all possible behaviors is infeasible. We propose a composable, model-free reinforcement learning method that learns a value function and an optimal policy for ea…

• Multi-Agent Model-Based Reinforcement Learning with Joint State-Action Learned Embeddings

  Zhizun Wang, David Meger · 16 February 2026

  Learning to coordinate many agents in partially observable and highly dynamic environments requires both informative representations and data-efficient training. To address this challenge, we present a novel model-based multi-agent reinforcement learning framework that unifies joint state-action rep…

• Flow-Factory: A Unified Framework for Reinforcement Learning in Flow-Matching Models

  Bowen Ping, Chengyou Jia, Minnan Luo, Hangwei Qian, Ivor Tsang · 16 February 2026

  Reinforcement learning has emerged as a promising paradigm for aligning diffusion and flow-matching models with human preferences, yet practitioners face fragmented codebases, model-specific implementations, and engineering complexity. We introduce Flow-Factory, a unified framework that decouples al…

• Dual-Granularity Contrastive Reward via Generated Episodic Guidance for Efficient Embodied RL

  Xin Liu, Yixuan Li, Yuhui Chen, Yuxing Qin, Haoran Li, Dongbin Zhao · 16 February 2026

  Designing suitable rewards poses a significant challenge in reinforcement learning (RL), especially for embodied manipulation. Trajectory success rewards are suitable for human judges or model fitting, but the sparsity severely limits RL sample efficiency. While recent methods have effectively impro…