AIIR-MIX: Multi-Agent Reinforcement Learning Meets Attention Individual Intrinsic Reward Mixing Network
Deducing the contribution of each agent and assigning the corresponding reward to them is a crucial problem in cooperative Multi-Agent Reinforcement Learning (MARL). Previous studies try to resolve the issue through designing an intrinsic reward function, but the intrinsic reward is simply combined with the environment reward by summation in these studies, which makes the performance of their MARL framework unsatisfactory. We propose a novel method named Attention Individual Intrinsic Reward Mixing Network (AIIR-MIX) in MARL, and the contributions of AIIR-MIX are listed as follows:(a) we construct a novel intrinsic reward network based on the attention mechanism to make teamwork more effective. (b) we propose a Mixing network that is able to combine intrinsic and extrinsic rewards non-linearly and dynamically in response to changing conditions of the environment. We compare AIIR-MIX with many State-Of-The-Art (SOTA) MARL methods on battle games in StarCraft II. And the results demonstrate that AIIR-MIX performs admirably and can defeat the current advanced methods on average test win rate. To validate the effectiveness of AIIR-MIX, we conduct additional ablation studies. The results show that AIIR-MIX can dynamically assign each agent a real-time intrinsic reward in accordance with their actual contribution.
Code (0)
등록된 구현이 없습니다.
Tasks
Multi-agent Reinforcement LearningStarcraftStarcraft IIMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
FAIIR: Building Toward A Conversational AI Agent Assistant for Youth Mental Health Service Provision
The world's healthcare systems and mental health agencies face both a growing demand for youth mental health services, alongside a simultaneous challenge of limited resources. Here, we focus on frontline crisis support, …
AI AgentTAGDynamic Noises of Multi-Agent Environments Can Improve Generalization: Agent-based Models meets Reinforcement Learning
We study the benefits of reinforcement learning (RL) environments based on agent-based models (ABM). While ABMs are known to offer microfoundational simulations at the cost of computational complexity, we empirically sho…
reinforcement-learningReinforcement Learning (RL)Graph Convolutional Reinforcement Learning for Collaborative Queuing Agents
In this paper, we explore the use of multi-agent deep learning as well as learning to cooperate principles to meet stringent service level agreements, in terms of throughput and end-to-end delay, for a set of classified …
Multi-agent Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Pessimism meets VCG: Learning Dynamic Mechanism Design via Offline Reinforcement Learning
Dynamic mechanism design has garnered significant attention from both computer scientists and economists in recent years. By allowing agents to interact with the seller over multiple rounds, where agents' reward function…
Offline RLreinforcement-learningReinforcement Learning (RL)Coordinated Exploration in Concurrent Reinforcement Learning
We consider a team of reinforcement learning agents that concurrently learn to operate in a common environment. We identify three properties - adaptivity, commitment, and diversity - which are necessary for efficient coo…
Diversityreinforcement-learningReinforcement LearningReinforcement Learning (RL)