Reinforcement Learning in Robotics

Neueste Paper

• RIZE: Adaptive Regularization for Imitation Learning

  Adib Karimi, Mohammad Mehdi Ebadzadeh · 20. November 2025

  We propose a novel Inverse Reinforcement Learning (IRL) method that mitigates the rigidity of fixed reward structures and the limited flexibility of implicit reward regularization. Building on the Maximum Entropy IRL framework, our approach incorporates a squared temporal-difference (TD) regularizer…

• Learning Human-Like RL Agents Through Trajectory Optimization With Action Quantization

  Jian-Ting Guo, Yu-Cheng Chen, Ping-Chun Hsieh, Kuo-Hao Ho, Po-Wei Huang, Ti-Rong Wu, I-Chen Wu · 20. November 2025

  Human-like agents have long been one of the goals in pursuing artificial intelligence. Although reinforcement learning (RL) has achieved superhuman performance in many domains, relatively little attention has been focused on designing human-like RL agents. As a result, many reward-driven RL agents o…

• Continual Reinforcement Learning for Cyber-Physical Systems: Lessons Learned and Open Challenges

  Kim N. Nolle, Ivana Dusparic, Rhodri Cusack, Vinny Cahill · 20. November 2025

  Continual learning (CL) is a branch of machine learning that aims to enable agents to adapt and generalise previously learned abilities so that these can be reapplied to new tasks or environments. This is particularly useful in multi-task settings or in non-stationary environments, where the dynamic…

• EntroPIC: Towards Stable Long-Term Training of LLMs via Entropy Stabilization with Proportional-Integral Control

  Kai Yang, Xin Xu, Yangkun Chen, Weijie Liu, Jiafei Lyu, Zichuan Lin, Deheng Ye, Saiyong Yang · 20. November 2025

  Long-term training of large language models (LLMs) requires maintaining stable exploration to prevent the model from collapsing into sub-optimal behaviors. Entropy is crucial in this context, as it controls exploration and helps avoid premature convergence to sub-optimal solutions. However, existing…

• The Impact of Quantization on Large Reasoning Model Reinforcement Learning

  Medha Kumar, Zifei Xu, Xin Wang, Tristan Webb · 20. November 2025

  Strong reasoning capabilities can now be achieved by large-scale reinforcement learning (RL) without any supervised fine-tuning. Although post-training quantization (PTQ) and quantization-aware training (QAT) are well studied in the context of fine-tuning, how quantization impacts RL in large reason…

• Empowering Multi-Turn Tool-Integrated Reasoning with Group Turn Policy Optimization

  Yifeng Ding, Hung Le, Songyang Han, Kangrui Ruan, Zhenghui Jin, Varun Kumar, Zijian Wang, Anoop Deoras · 20. November 2025

  Training Large Language Models (LLMs) for multi-turn Tool-Integrated Reasoning (TIR) - where models iteratively reason, generate code, and verify through execution - remains challenging for existing reinforcement learning (RL) approaches. Current RL methods, exemplified by Group Relative Policy Opti…

• Learning Where, What and How to Transfer: A Multi-Role Reinforcement Learning Approach for Evolutionary Multitasking

  Jiajun Zhan, Zeyuan Ma, Yue-Jiao Gong, Kay Chen Tan · 20. November 2025

  Evolutionary multitasking (EMT) algorithms typically require tailored designs for knowledge transfer, in order to assure convergence and optimality in multitask optimization. In this paper, we explore designing a systematic and generalizable knowledge transfer policy through Reinforcement Learning. …

• Parallelizing Tree Search with Twice Sequential Monte Carlo

  Yaniv Oren, Joery A. de Vries, Pascal R. van der Vaart, Matthijs T. J. Spaan, Wendelin B\"ohmer · 19. November 2025

  Model-based reinforcement learning (RL) methods that leverage search are responsible for many milestone breakthroughs in RL. Sequential Monte Carlo (SMC) recently emerged as an alternative to the Monte Carlo Tree Search (MCTS) algorithm which drove these breakthroughs. SMC is easier to parallelize a…

• FairDICE: Fairness-Driven Offline Multi-Objective Reinforcement Learning

  Woosung Kim, Jinho Lee, Jongmin Lee, Byung-Jun Lee · 19. November 2025

  Multi-objective reinforcement learning (MORL) aims to optimize policies in the presence of conflicting objectives, where linear scalarization is commonly used to reduce vector-valued returns into scalar signals. While effective for certain preferences, this approach cannot capture fairness-oriented …

• ReflexGrad: Three-Way Synergistic Architecture for Zero-Shot Generalization in LLM Agents

  Ankush Kadu, Ashwanth Krishnan · 19. November 2025

  Enabling agents to learn from experience and generalize across diverse tasks without task-specific training remains a fundamental challenge in reinforcement learning and decision-making. While recent approaches have explored episodic memory (Reflexion), gradient-based prompt optimization (TextGrad),…

• Fair-GNE : Generalized Nash Equilibrium-Seeking Fairness in Multiagent Healthcare Automation

  Promise Ekpo, Saesha Agarwal, Felix Grimm, Lekan Molu, Angelique Taylor · 19. November 2025

  Enforcing a fair workload allocation among multiple agents tasked to achieve an objective in learning enabled demand side healthcare worker settings is crucial for consistent and reliable performance at runtime. Existing multi-agent reinforcement learning (MARL) approaches steer fairness by shaping …

• Structured Imitation Learning of Interactive Policies through Inverse Games

  Max M. Sun, Todd Murphey · 18. November 2025

  Generative model-based imitation learning methods have recently achieved strong results in learning high-complexity motor skills from human demonstrations. However, imitation learning of interactive policies that coordinate with humans in shared spaces without explicit communication remains challeng…

• NFQ2.0: The CartPole Benchmark Revisited

  Sascha Lange, Roland Hafner, Martin Riedmiller · 18. November 2025

  This article revisits the 20-year-old neural fitted Q-iteration (NFQ) algorithm on its classical CartPole benchmark. NFQ was a pioneering approach towards modern Deep Reinforcement Learning (Deep RL) in applying multi-layer neural networks to reinforcement learning for real-world control problems. W…

• Accelerated Distributional Temporal Difference Learning with Linear Function Approximation

  Kaicheng Jin, Yang Peng, Jiansheng Yang, Zhihua Zhang · 18. November 2025

  In this paper, we study the finite-sample statistical rates of distributional temporal difference (TD) learning with linear function approximation. The purpose of distributional TD learning is to estimate the return distribution of a discounted Markov decision process for a given policy. Previous wo…

• Beyond Fixed Tasks: Unsupervised Environment Design for Task-Level Pairs

  Daniel Furelos-Blanco, Charles Pert, Frederik Kelbel, Alex F. Spies, Alessandra Russo, Michael Dennis · 18. November 2025

  Training general agents to follow complex instructions (tasks) in intricate environments (levels) remains a core challenge in reinforcement learning. Random sampling of task-level pairs often produces unsolvable combinations, highlighting the need to co-design tasks and levels. While unsupervised en…

• STEP: Success-Rate-Aware Trajectory-Efficient Policy Optimization

  Yuhan Chen, Yuxuan Liu, Long Zhang, Pengzhi Gao, Jian Luan, Wei Liu · 18. November 2025

  Multi-turn interaction remains challenging for online reinforcement learning. A common solution is trajectory-level optimization, which treats each trajectory as a single training sample. However, this approach can be inefficient and yield misleading learning signals: it applies uniform sampling acr…

• Expressive Temporal Specifications for Reward Monitoring

  Omar Adalat, Francesco Belardinelli · 18. November 2025

  Specifying informative and dense reward functions remains a pivotal challenge in Reinforcement Learning, as it directly affects the efficiency of agent training. In this work, we harness the expressive power of quantitative Linear Temporal Logic on finite traces (($\text{LTL}_f[\mathcal{F}]$)) to sy…

• One-Step Generative Policies with Q-Learning: A Reformulation of MeanFlow

  Zeyuan Wang, Da Li, Yulin Chen, Ye Shi, Liang Bai, Tianyuan Yu, Yanwei Fu · 18. November 2025

  We introduce a one-step generative policy for offline reinforcement learning that maps noise directly to actions via a residual reformulation of MeanFlow, making it compatible with Q-learning. While one-step Gaussian policies enable fast inference, they struggle to capture complex, multimodal action…

• Transformer-Based Scalable Multi-Agent Reinforcement Learning for Networked Systems with Long-Range Interactions

  Vidur Sinha, Muhammed Ustaomeroglu, Guannan Qu · 18. November 2025

  Multi-agent reinforcement learning (MARL) has shown promise for large-scale network control, yet existing methods face two major limitations. First, they typically rely on assumptions leading to decay properties of local agent interactions, limiting their ability to capture long-range dependencies s…

• Soft Conflict-Resolution Decision Transformer for Offline Multi-Task Reinforcement Learning

  Shudong Wang, Xinfei Wang, Chenhao Zhang, Shanchen Pang, Haiyuan Gui, Wenhao Ji, Xiaojian Liao · 18. November 2025

  Multi-task reinforcement learning (MTRL) seeks to learn a unified policy for diverse tasks, but often suffers from gradient conflicts across tasks. Existing masking-based methods attempt to mitigate such conflicts by assigning task-specific parameter masks. However, our empirical study shows that co…

• DiffFP: Learning Behaviors from Scratch via Diffusion-based Fictitious Play

  Akash Karthikeyan, Yash Vardhan Pant · 18. November 2025

  Self-play reinforcement learning has demonstrated significant success in learning complex strategic and interactive behaviors in competitive multi-agent games. However, achieving such behaviors in continuous decision spaces remains challenging. Ensuring adaptability and generalization in self-play s…

• Scalable Multi-Objective and Meta Reinforcement Learning via Gradient Estimation

  Zhenshuo Zhang, Minxuan Duan, Youran Ye, Hongyang R. Zhang · 18. November 2025

  We study the problem of efficiently estimating policies that simultaneously optimize multiple objectives in reinforcement learning (RL). Given $n$ objectives (or tasks), we seek the optimal partition of these objectives into $k \ll n$ groups, where each group comprises related objectives that can be…

• Explainable RL Policies by Distilling to Locally-Specialized Linear Policies with Voronoi State Partitioning

  Senne Deproost, Dennis Steckelmacher, Ann Now\'e · 18. November 2025

  Deep Reinforcement Learning is one of the state-of-the-art methods for producing near-optimal system controllers. However, deep RL algorithms train a deep neural network, that lacks transparency, which poses challenges when the controller has to meet regulations, or foster trust. To alleviate this, …

• Goal-Oriented Multi-Agent Reinforcement Learning for Decentralized Agent Teams

  Hung Du, Hy Nguyen, Srikanth Thudumu, Rajesh Vasa, Kon Mouzakis · 18. November 2025

  Connected and autonomous vehicles across land, water, and air must often operate in dynamic, unpredictable environments with limited communication, no centralized control, and partial observability. These real-world constraints pose significant challenges for coordination, particularly when vehicles…

• Efficient Reinforcement Learning for Zero-Shot Coordination in Evolving Games

  Bingyu Hui, Lebin Yu, Quanming Yao, Yunpeng Qu, Xudong Zhang, Jian Wang · 18. November 2025

  Zero-shot coordination(ZSC) has become a hot topic in reinforcement learning research recently. It focuses on the generalization ability of agents, requiring them to coordinate well with collaborators that are not seen before without any fine-tuning. Population-based training has been proven to prov…