DCIR: Dynamic Consistency Intrinsic Reward For Multi-agent Reinforcement Learning

Abstract

Learning optimal behavior policy for each agent in multi-agent systems is an essential yet difficult problem. Despite fruitful progress in multi-agent reinforcement learning, the challenge of addressing the dynamics of whether two agents should exhibit consistent behaviors is still under-explored. In this paper, we propose a new approach that enables agents to learn whether their behaviors should be consistent with that of other agents by utilizing intrinsic rewards to learn the optimal policy for each agent. We begin by defining behavior consistency as the divergence in output actions between two agents when provided with the same observation. Subsequently, we introduce dynamic consistency intrinsic reward (DCIR) to stimulate agents to be aware of others' behaviors and determine whether to be consistent with them. Lastly, we devise a dynamic scale network (DSN) that provides learnable scale factors for the agent at every time step to dynamically ascertain whether to award consistent b

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keylin2023dcir

Related papers

• Coordinated Exploration Via Intrinsic Rewards For Multi-agent Reinforcement Learning (2019)0.00
• Intrinsic Action Tendency Consistency For Cooperative Multi-agent Reinforcement Learning (2024)5.24
• Discovering Individual Rewards In Collective Behavior Through Inverse Multi-agent Reinforcement Learning (2023)0.00
• Exploration With Unreliable Intrinsic Reward In Multi-agent Reinforcement Learning (2019)0.00
• Influence-based Reinforcement Learning For Intrinsically-motivated Agents (2021)0.00
• BCR-DRL: Behavior- And Context-aware Reward For Deep Reinforcement Learning In Human-ai Coordination (2024)0.00
• Social Influence As Intrinsic Motivation For Multi-agent Deep Reinforcement Learning (2018)0.00
• Distributional Reward Estimation For Effective Multi-agent Deep Reinforcement Learning (2022)0.00