Reward Design for RL

RL: Reinforcement Learning

Overview

Reward design studies how to turn task goals, preferences, and constraints into learning signals, especially when success is sparse or objectives compete. Approaches include potential-based shaping and reward machines, preference and rubric models, visual progress rewards, intrinsic exploration bonuses, and automated reward search using language models. These methods are used in settings from robot manipulation and locomotion to language-model reasoning, tool use, and multi-agent coordination. A central tension is that denser or adaptive rewards can improve credit assignment but also mislead policies, destabilize training, or invite reward hacking, so evaluation must test intended outcomes rather than proxy scores alone.

Latest papers

CardsList

290 papers37 papers in the last four weeks, down 16% on the four weeks before. 0.3% of all new papers.

  1. Reward-Zero: Language Embedding Driven Implicit Reward Mechanisms for Reinforcement Learning

    Mar 10, 2026Heng Zhang, Haddy Alchaer, Arash Ajoudani +1Reward Design for RLDense Reward RL

  2. Decoupling Task and Behavior: A Two-Stage Reward Curriculum in Reinforcement Learning for Robotics

    Mar 5, 2026Kilian Freitag, Knut Åkesson, Morteza Haghir ChehreghaniRL for RoboticsReinforcement Learning

  3. RLAR: An Agentic Reward System for Multi-task Reinforcement Learning on Large Language Models

    Feb 28, 2026Andrew Zhuoer Feng, Cunxiang Wang, Bosi Wen +4RL for Language ModelsReward Design for RL

  4. Keyframe-Guided Structured Rewards for Reinforcement Learning in Long-Horizon Laboratory Robotics

    Feb 28, 2026Yibo Qiu, Shu'ang Sun, Haoliang Ye +2Long-Horizon Robotic ManipulationRobotic RL

  5. Adaptive Correlation-Weighted Intrinsic Rewards for Reinforcement Learning

    Feb 27, 2026Viet Bac Nguyen, Phuong Thai NguyenIntrinsic Reward MethodsReward Design for RL

  6. RF-Agent: Automated Reward Function Design via Language Agent Tree Search

    Feb 27, 2026Ning Gao, Xiuhui Zhang, Xingyu Jiang +3Reward Design for RLRL Control

  7. SibylSense: Adaptive Rubric Learning via Memory Tuning and Adversarial Probing

    Feb 24, 2026Yifei Xu, Guilherme Potje, Shivam Shandilya +9Rubric-Based RLReward Design for RL

  8. How to Train Your Deep Research Agent? Prompt, Reward, and Policy Optimization in Search-R1

    Feb 23, 2026Yinuo Xu, Shuo Lu, Jianjie Cheng +5RL for LLM AgentsAutonomous Research Agents

  9. PRISM: Parallel Reward Integration with Symmetry for MORL

    Feb 20, 2026Finn van der Knaap, Kejiang Qian, Zheng Xu +1Equivariant Policy LearningReinforcement Learning

  10. Fairness over Equality: Correcting Social Incentives in Asymmetric Sequential Social Dilemmas

    Feb 17, 2026Alper Demir, Hüseyin Aydın, Kale-ab Abebe Tessera +2Cooperative MARLMulti-Agent Reinforcement Learning

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

    Feb 16, 2026Elias Malomgré, Pieter SimoensAI AlignmentReinforcement Learning

  12. SLOPE: Optimistic Potential Landscape Shaping for Model-based Reinforcement Learning

    Feb 3, 2026Yao-Hui Li, Zeyu Wang, Xin Li +7Model-Based RLSparse-Reward RL

  13. The Trajectory Alignment Coefficient in Two Acts: From Reward Tuning to Reward Learning

    Jan 23, 2026Calarina Muslimani, Yunshu Du, Kenta Kawamoto +3Reward Design for RLReward Modeling

  14. Dual-Evolving Reinforcement Learning for Automated Reward Design

    Dec 15, 2025Sitao Cheng, Tianle Li, Xuhan Huang +2Reward Design for RLReinforcement Learning

  15. Reinforcement Learning for Long-Horizon Unordered Tasks: From Boolean to Coupled Reward Machines

    Oct 31, 2025Kristina Levina, Nikolaos Pappas, Athanasios Karapantelakis +2Reward MachinesReinforcement Learning

  16. Gain Tuning Is Not What You Need: Reward Gain Adaptation for Constrained Locomotion Learning

    Oct 12, 2025Arthicha Srisuchinnawong, Poramate ManoonpongConstrained RLRL for Legged Locomotion

  17. Towards Shutdownable Agents via Stochastic Choice

    Jun 30, 2024Elliott Thornley, Alexander Roman, Christos Ziakas +2CorrigibilityAI Agent Safety