mlsanityData to 14 Oct 2026

BCR-DRL: Behavior- and Context-aware Reward for Deep Reinforcement Learning in Human-AI Coordination

arXiv 2408.07877 ↗First posted 15 Aug 2024cs.AI cs.LGcited by 3

On the map: Deep reinforcement learning methods → Deep RL algorithms and representations

Abstract (arXiv)

Deep reinforcement Learning (DRL) offers a powerful framework for training AI agents to coordinate with human partners. However, DRL faces two critical challenges in human-AI coordination (HAIC): sparse rewards and unpredictable human behaviors. These challenges significantly limit DRL to identify effective coordination policies, due to its impaired capability of optimizing exploration and exploitation. To address these limitations, we propose an innovative behavior- and context-aware reward (BCR) for DRL, which optimizes exploration and exploitation by leveraging human behaviors and contextual information in HAIC. Our BCR consists of two components: (i) A novel dual intrinsic rewarding scheme to enhance exploration. This scheme composes an AI self-motivated intrinsic reward and a human-motivated intrinsic reward, which are designed to increase the capture of sparse rewards by a logarithmic-based strategy; and (ii) A new context-aware weighting mechanism for the designed rewards to improve exploitation. This mechanism helps the AI agent prioritize actions that better coordinate with the human partner by utilizing contextual information that can reflect the evolution of learning. Extensive simulations in the Overcooked environment demonstrate that our approach can increase the cumulative sparse rewards by approximately 20%, and improve the sample efficiency by around 38% compared to state-of-the-art baselines.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 19 of its 26 references that are in the map. First posted on arXiv 15 Aug 2024.

Builds on

19 of 26 references.

References · 19

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  3. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,258
  4. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,558
  5. 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,194
  6. 2018End-to-End Multi-Task Learning with Attentioncited by 534
  7. 2020Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 485
  8. 2019On the Utility of Learning about Humans for Human-AI Coordinationcited by 349
  9. 2016Cooperative Inverse Reinforcement Learningcited by 300
  10. 2020Learning to Utilize Shaping Rewards: A New Approach of Reward Shapingcited by 114
  11. 2021Maximum Entropy Population-Based Training for Zero-Shot Human-AI Coordinationcited by 70
  12. 2022The Effect of Modeling Human Rationality Level on Learning Rewards from Multiple Feedback Typescited by 26
7 more
  1. 2024Towards Optimizing Human-Centric Objectives in AI-Assisted Decision-Making With Offline Reinforcement Learningcited by 13
  2. 2021PantheonRL: A MARL Library for Dynamic Training Interactionscited by 10
  3. 2018Efficiently Combining Human Demonstrations and Interventions for Safe Training of Autonomous Systems in Real-Timecited by 8
  4. 2023A Hierarchical Approach to Population Training for Human-AI Collaborationcited by 7
  5. 2023Secure Deep Reinforcement Learning for Dynamic Resource Allocation in Wireless MEC Networkscited by 2
  6. 2023Hybrid-Task Meta-Learning: A GNN Approach for Scalable and Transferable Bandwidth Allocationcited by 1
  7. 2024A Constrained Deep Reinforcement Learning Optimization for Reliable Network Slicing in a Blockchain-Secured Low-Latency Wireless Networkcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025Adaptive XAI in High Stakes Environments: Modeling Swift Trust with Multimodal Feedback in Human AI Teamscited by 0
  2. 2026Adaptive Human-AI Coordination via Hierarchical Action Disentanglementcited by 0
  3. 2026Partner-Aware Hierarchical Skill Discovery for Robust Human-AI Collaborationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Reward Models in Deep Reinforcement Learning: A Survey
  2. 2024Effective Reward Specification in Deep Reinforcement Learning
  3. 2024TLCR: Token-Level Continuous Reward for Fine-grained Reinforcement Learning from Human Feedback
  4. 2026Hierarchical Reward Design from Language: Enhancing Alignment of Agent Behavior with Human Specifications
  5. 2024REvolve: Reward Evolution with Large Language Models using Human Feedback
  6. 2024Decision Theory-Guided Deep Reinforcement Learning for Fast Learning
  7. 2024A Comprehensive Survey of Reinforcement Learning: From Algorithms to Practical Challenges
  8. 2025A Practical Introduction to Deep Reinforcement Learning