Credit Assignment in RL

RL: Reinforcement Learning

Ask about this topic

Overview

Credit assignment asks which decisions deserve credit or blame when rewards arrive late or apply to an entire trajectory, a central problem in long-horizon and cooperative tasks. Traditional approaches include temporal-difference learning, eligibility traces, critics and advantage estimation, while reward shaping, counterfactual comparisons, and Shapley values offer ways to make contributions more explicit. Recent work on language-model agents often assigns feedback at the token, step, or turn level using process rewards, hindsight, trajectory graphs, or comparisons between alternative rollouts; related methods address multi-agent control and robotics. The key tension is that denser signals can improve learning but may be noisy, biased, or expensive, and it remains difficult to establish that a local action actually caused progress rather than merely accompanied it.

Latest papers

CardsList

219 papers47 papers in the last four weeks, up 88% on the four weeks before. 0.3% of all new papers.

  1. Learning When to Act: Interval-Aware Reinforcement Learning with Predictive Temporal Structure

    Mar 23, 2026Davide Di GioiaContinuous-Time RLCredit Assignment in RL

    University College London

  2. RewardFlow: Topology-Aware Reward Propagation on State Graphs for Agentic RL with Large Language Models

    Mar 19, 2026Xiao Feng, Bo Han, Zhanke Zhou +5RL for LLM AgentsReward Design for RL

    TMLR Group, Hong Kong Baptist University · TCL Corporate Research (HK) Co., Ltd · Cooperative Medianet Innovation Center, Shanghai Jiao Tong University +1

  3. HISR: Hindsight Information Modulated Segmental Process Rewards For Multi-turn Agentic Reinforcement Learning

    Mar 19, 2026Zhicong Lu, Zichuan Lin, Wei Jia +7RL for LLM AgentsAgentic RL

    Aerospace Information Research Institute, Chinese Academy of Sciences · University of Chinese Academy of Sciences · Tencent Hunyuan +1

  4. Hindsight Credit Assignment for Long-Horizon LLM Agents

    Mar 7, 2026Hui-Ze Tan, Xiao-Wen Yang, Hao Chen +7Credit Assignment in RLLong-Horizon LLM Agents

    State Key Laboratory of Novel Software Technology, Nanjing University, China · School of Artificial Intelligence, Nanjing University, China · FiT, Tencent, Shenzhen, China +2

  5. MICA: Multi-granularity Intertemporal Credit Assignment for Long-Horizon Emotional Support Dialogue

    Mar 6, 2026Naifan Zhang, Ruihan Sun, Jinwei Su +4RL for Language ModelsCredit Assignment in RL

    NatureSelect · Tsinghua University · South China Normal University +1

  6. Harmonizing Dense and Sparse Signals in Multi-turn RL: Dual-Horizon Credit Assignment for Industrial Sales Agents

    Mar 2, 2026Haojin Yang, Ai Jian, Xinyue Huang +5RL for LLM AgentsReinforcement Learning

    Peking University · Beijing University of Posts and Telecommunications · Sun Yat-sen University +2

  7. Explicit Credit Assignment through Local Rewards and Dependence Graphs in Multi-Agent Reinforcement Learning

    Jan 29, 2026Bang Giang Le, Viet Cuong TaCredit Assignment in RLCredit Assignment

    Human-Machine Interaction Laboratory VNU University of Engineering and Technology, Hanoi, Vietnam

  8. Who Gets the Reward & Who Gets the Blame? Evaluation-Aligned Training Signals for Multi-LLM Agents

    Nov 11, 2025Chih-Hsuan, Yang, Tanwi Mallick +5Multi-Agent LLM SystemsCooperative Game Theory

    Bella · Argonne National Laboratory · & University of Chicago

  9. TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels

    Apr 17, 2025Siow Meng Low, Ze Gong, Akshat KumarRL ControlCredit Assignment in RL

    School of Computing and Information Systems, Singapore Management University, Singapore · Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China