Reinforcement Learning in Robotics

Neueste Paper

• GRASP: Gradient Realignment via Active Shared Perception for Multi-Agent Collaborative Optimization

  Sihan Zhou, Tiantian He, Yifan Lu, Yaqing Hou, Yew-Soon Ong · 2. April 2026

  Non-stationarity arises from concurrent policy updates and leads to persistent environmental fluctuations. Existing approaches like Centralized Training with Decentralized Execution (CTDE) and sequential update schemes mitigate this issue. However, since the perception of the policies of other agent…

• Learning to Play Blackjack: A Curriculum Learning Perspective

  Amirreza Alasti, Efe Erdal, Y\"ucel Celik, Theresa Eimer · 2. April 2026

  Reinforcement Learning (RL) agents often struggle with efficiency and performance in complex environments. We propose a novel framework that uses a Large Language Model (LLM) to dynamically generate a curriculum over available actions, enabling the agent to incorporate each action individually. We a…

• Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG

  Aditi Singh, Abul Ehtesham, Saket Kumar, Tala Talaei Khoei, Athanasios V. Vasilakos · 2. April 2026

  Large Language Models (LLMs) have advanced artificial intelligence by enabling human-like text generation and natural language understanding. However, their reliance on static training data limits their ability to respond to dynamic, real-time queries, resulting in outdated or inaccurate outputs. Re…

• Full-Gradient Successor Feature Representations

  Ritish Shrirao, Aditya Priyadarshi, Raghuram Bharadwaj Diddigi · 2. April 2026

  Successor Features (SF) combined with Generalized Policy Improvement (GPI) provide a robust framework for transfer learning in Reinforcement Learning (RL) by decoupling environment dynamics from reward functions. However, standard SF learning methods typically rely on semi-gradient Temporal Differen…

• Learning to Hint for Reinforcement Learning

  Yu Xia, Canwen Xu, Zhewei Yao, Julian McAuley, Yuxiong He · 2. April 2026

  Group Relative Policy Optimization (GRPO) is widely used for reinforcement learning with verifiable rewards, but it often suffers from advantage collapse: when all rollouts in a group receive the same reward, the group yields zero relative advantage and thus no learning signal. For example, if a que…

• Temporal Memory for Resource-Constrained Agents: Continual Learning via Stochastic Compress-Add-Smooth

  Michael Chertkov · 2. April 2026

  An agent that operates sequentially must incorporate new experience without forgetting old experience, under a fixed memory budget. We propose a framework in which memory is not a parameter vector but a stochastic process: a Bridge Diffusion on a replay interval $[0,1]$, whose terminal marginal enco…

• Model-Based Learning of Near-Optimal Finite-Window Policies in POMDPs

  Philip Jordan, Maryam Kamgarpour · 2. April 2026

  We study model-based learning of finite-window policies in tabular partially observable Markov decision processes (POMDPs). A common approach to learning under partial observability is to approximate unbounded history dependencies using finite action-observation windows. This induces a finite-state …

• Go Big or Go Home: Simulating Mobbing Behavior with Braitenbergian Robots

  Elaheh Sanoubari · 2. April 2026

  We used the Webots robotics simulation platform to simulate a dyadic avoiding and mobbing predator behavior in a group of Braitenbergian robots. Mobbing is an antipredator adaptation used by some animals in which the individuals cooperatively attack or harass a predator to protect themselves. One wa…

• Flow-based Policy With Distributional Reinforcement Learning in Trajectory Optimization

  Ruijie Hao, Longfei Zhang, Yang Dai, Yang Ma, Xingxing Liang, Guangquan Cheng · 2. April 2026

  Reinforcement Learning (RL) has proven highly effective in addressing complex control and decision-making tasks. However, in most traditional RL algorithms, the policy is typically parameterized as a diagonal Gaussian distribution, which constrains the policy from capturing multimodal distributions,…

• Offline Constrained RLHF with Multiple Preference Oracles

  Brenden Latham, Mehrdad Moharrami · 2. April 2026

  We study offline constrained reinforcement learning from human feedback with multiple preference oracles. Motivated by applications that trade off performance with safety or fairness, we aim to maximize target population utility subject to a minimum protected group welfare constraint. From pairwise …

• HiMA-Ecom: Enabling Joint Training of Hierarchical Multi-Agent E-commerce Assistants

  Junxing Hu, Ai Han, Haolan Zhan, Pu Wei, Zhiqian Zhang, Yuhang Guo, Jiawei Lu, Zhen Chen, Haoran Li, Zicheng Zhang · 2. April 2026

  Hierarchical multi-agent systems based on large language models (LLMs) have become a common paradigm for building AI assistants in vertical domains such as e-commerce, where a master agent coordinates multiple specialized sub-agents. Despite their practical importance, realistic benchmarks for train…

• Analysis of On-policy Policy Gradient Methods under the Distribution Mismatch

  Weizhen Wang, Jianping He, Xiaoming Duan · 2. April 2026

  Policy gradient methods are one of the most successful approaches for solving challenging reinforcement learning problems. Despite their empirical successes, many state-of-the-art policy gradient algorithms for discounted problems deviate from the theoretical policy gradient theorem due to the exist…

• Internal State-Based Policy Gradient Methods for Partially Observable Markov Potential Games

  Wonseok Yang, Thinh T. Doan · 2. April 2026

  This letter studies multi-agent reinforcement learning in partially observable Markov potential games. Solving this problem is challenging due to partial observability, decentralized information, and the curse of dimensionality. First, to address the first two challenges, we leverage the common info…

• Generalizable Dense Reward for Long-Horizon Robotic Tasks

  Silong Yong, Stephen Sheng, Carl Qi, Xiaojie Wang, Evan Sheehan, Anurag Shivaprasad, Yaqi Xie, Katia Sycara, Yesh Dattatreya · 2. April 2026

  Existing robotic foundation policies are trained primarily via large-scale imitation learning. While such models demonstrate strong capabilities, they often struggle with long-horizon tasks due to distribution shift and error accumulation. While reinforcement learning (RL) can finetune these models,…

• RefineRL: Advancing Competitive Programming with Self-Refinement Reinforcement Learning

  Shaopeng Fu, Xingxing Zhang, Li Dong, Di Wang, Furu Wei · 2. April 2026

  While large language models (LLMs) have demonstrated strong performance on complex reasoning tasks such as competitive programming (CP), existing methods predominantly focus on single-attempt settings, overlooking their capacity for iterative refinement. In this paper, we present RefineRL, a novel a…

• Evolution Strategies for Deep RL pretraining

  Adrian Mart\'inez, Ananya Gupta, Hanka Goralija, Mario Rico, Sa\'ul Fenollosa, Tamar Alphaidze · 2. April 2026

  Although Deep Reinforcement Learning has proven highly effective for complex decision-making problems, it demands significant computational resources and careful parameter adjustment in order to develop successful strategies. Evolution strategies offer a more straightforward, derivative-free approac…

• Zero-Shot Coordination in Ad Hoc Teams with Generalized Policy Improvement and Difference Rewards

  Rupal Nigam, Niket Parikh, Hamid Osooli, Mikihisa Yuasa, Jacob Heglund, Huy T. Tran · 1. April 2026

  Real-world multi-agent systems may require ad hoc teaming, where an agent must coordinate with other previously unseen teammates to solve a task in a zero-shot manner. Prior work often either selects a pretrained policy based on an inferred model of the new teammates or pretrains a single policy tha…

• ASI-Evolve: AI Accelerates AI

  Weixian Xu, Tiantian Mi, Yixiu Liu, Yang Nan, Zhimeng Zhou, Lyumanshan Ye, Lin Zhang, Yu Qiao, Pengfei Liu · 1. April 2026

  Can AI accelerate the development of AI itself? While recent agentic systems have shown strong performance on well-scoped tasks with rapid feedback, it remains unclear whether they can tackle the costly, long-horizon, and weakly supervised research loops that drive real AI progress. We present ASI-E…

• MemFactory: Unified Inference & Training Framework for Agent Memory

  Ziliang Guo, Ziheng Li, Zhiyu Li · 1. April 2026

  Memory-augmented Large Language Models (LLMs) are essential for developing capable, long-term AI agents. Recently, applying Reinforcement Learning (RL) to optimize memory operations, such as extraction, updating, and retrieval, has emerged as a highly promising research direction. However, existing …

• Masked IRL: LLM-Guided Reward Disambiguation from Demonstrations and Language

  Minyoung Hwang, Alexandra Forsey-Smerek, Nathaniel Dennler, Andreea Bobu · 1. April 2026

  Robots can adapt to user preferences by learning reward functions from demonstrations, but with limited data, reward models often overfit to spurious correlations and fail to generalize. This happens because demonstrations show robots how to do a task but not what matters for that task, causing the …

• Target-Aligned Reinforcement Learning

  Leonard S. Pleiss, James Harrison, Maximilian Schiffer · 1. April 2026

  Many reinforcement learning algorithms rely on target networks - lagged copies of the online network - to stabilize training. While effective, this mechanism introduces a fundamental stability-recency tradeoff: slower target updates improve stability but reduce the recency of learning signals, hinde…

• Stability and Sensitivity Analysis of Relative Temporal-Difference Learning: Extended Version

  Masoud S. Sakha, Rushikesh Kamalapurkar, Sean Meyn · 31. März 2026

  Relative temporal-difference (TD) learning was introduced to mitigate the slow convergence of TD methods when the discount factor approaches one by subtracting a baseline from the temporal-difference update. While this idea has been studied in the tabular setting, stability guarantees with function …

• Reducing Oracle Feedback with Vision-Language Embeddings for Preference-Based RL

  Udita Ghosh, Dripta S. Raychaudhuri, Jiachen Li, Konstantinos Karydis, Amit Roy-Chowdhury · 31. März 2026

  Preference-based reinforcement learning can learn effective reward functions from comparisons, but its scalability is constrained by the high cost of oracle feedback. Lightweight vision-language embedding (VLE) models provide a cheaper alternative, but their noisy outputs limit their effectiveness a…

• FlowRL: A Taxonomy and Modular Framework for Reinforcement Learning with Diffusion Policies

  Chenxiao Gao, Edward Chen, Tianyi Chen, Bo Dai · 31. März 2026

  Thanks to their remarkable flexibility, diffusion models and flow models have emerged as promising candidates for policy representation. However, efficient reinforcement learning (RL) upon these policies remains a challenge due to the lack of explicit log-probabilities for vanilla policy gradient es…

• Diagnosing Non-Markovian Observations in Reinforcement Learning via Prediction-Based Violation Scoring

  Naveen Mysore · 31. März 2026

  Reinforcement learning algorithms assume that observations satisfy the Markov property, yet real-world sensors frequently violate this assumption through correlated noise, latency, or partial observability. Standard performance metrics conflate Markov breakdowns with other sources of suboptimality, …