Multi-agent Policy Optimization with Approximatively Synchronous Advantage Estimation
Cooperative multi-agent tasks require agents to deduce their own contributions with shared global rewards, known as the challenge of credit assignment. General methods for policy based multi-agent reinforcement learning to solve the challenge introduce differentiate value functions or advantage functions for individual agents. In multi-agent system, polices of different agents need to be evaluated jointly. In order to update polices synchronously, such value functions or advantage functions also need synchronous evaluation. However, in current methods, value functions or advantage functions use counter-factual joint actions which are evaluated asynchronously, thus suffer from natural estimation bias. In this work, we propose the approximatively synchronous advantage estimation. We first derive the marginal advantage function, an expansion from single-agent advantage function to multi-agent system. Further more, we introduce a policy approximation for synchronous advantage estimation, and break down the multi-agent policy optimization problem into multiple sub-problems of single-agent policy optimization. Our method is compared with baseline algorithms on StarCraft multi-agent challenges, and shows the best performance on most of the tasks.
Code (0)
등록된 구현이 없습니다.
Tasks
Multi-agent Reinforcement LearningStarcraftSimilar Papers 제목 키워드 기반
RTPO: Reverse-Turn Policy Optimization for Stabilizing Agentic RL Training
Training multi-turn agentic workflows with reinforcement learning (RL) enables large language models to perform complex reasoning, use external tools, and conduct iterative search beyond single-turn settings. Yet multi-t…
Reinforcement LearningSingle-Rollout Asynchronous Optimization for Agentic Reinforcement Learning
Reinforcement learning (RL) is becoming increasingly important for post-training large language models (LLMs). Previous RL pipelines for LLMs were mostly synchronous and batch-interleaved, which is inefficient for long-h…
Reinforcement LearningEnhancing Spectrum Efficiency in 6G Satellite Networks: A GAIL-Powered Policy Learning via Asynchronous Federated Inverse Reinforcement Learning
In this paper, a novel generative adversarial imitation learning (GAIL)-powered policy learning approach is proposed for optimizing beamforming, spectrum allocation, and remote user equipment (RUE) association in NTNs. T…
Federated LearningImitation LearningReinforcement Learning (RL)$\boldsymbol{f}$-OPD: Stabilizing Long-Horizon On-Policy Distillation with Freshness-Aware Control
Scaling on-policy distillation (OPD) for large language models (LLMs) confronts a fundamental tension: asynchronous execution is necessary for system efficiency, but structurally deviates from the ideal on-policy objecti…
ASYNCHRONOUS MULTI-AGENT GENERATIVE ADVERSARIAL IMITATION LEARNING
Imitation learning aims to inversely learn a policy from expert demonstrations, which has been extensively studied in the literature for both single-agent setting with Markov decision process (MDP) model, and multi-agent…
Decision MakingImitation Learning