Variational Policy Propagation for Multi-agent Reinforcement Learning

2020-04-19 · Chao Qu, Hui Li, Chang Liu, Junwu Xiong, James Zhang, Wei Chu, Weiqiang Wang, Yuan Qi, Le Song

We propose a \emph{collaborative} multi-agent reinforcement learning algorithm named variational policy propagation (VPP) to learn a \emph{joint} policy through the interactions over agents. We prove that the joint policy is a Markov Random Field under some mild conditions, which in turn reduces the policy space effectively. We integrate the variational inference as special differentiable layers in policy such that the actions can be efficiently sampled from the Markov Random Field and the overall policy is differentiable. We evaluate our algorithm on several large scale challenging tasks and demonstrate that it outperforms previous state-of-the-arts.

📄 PDF Abstract BibTeX arXiv:2004.08883

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Variational Inference

A Variational Approach to Mutual Information-Based Coordination for Multi-Agent Reinforcement Learning

2023-03-01 · Woojun Kim, Whiyoung Jung, Myungsik Cho, Youngchul Sung

In this paper, we propose a new mutual information framework for multi-agent reinforcement learning to enable multiple agents to learn coordinated behaviors by regularizing the accumulated return with the simultaneous mu…

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Bayesian Ego-graph Inference for Networked Multi-Agent Reinforcement Learning

2025-09-20 · Wei Duan, Jie Lu, Junyu Xuan arxiv

In networked multi-agent reinforcement learning (Networked-MARL), decentralized agents must act under local observability and constrained communication over fixed physical graphs. Existing methods often assume static nei…

Multi-agent Reinforcement Learning

Value Propagation for Decentralized Networked Deep Multi-agent Reinforcement Learning

2019-01-27 · NeurIPS 2019 12 · Chao Qu, Shie Mannor, Huan Xu, Yuan Qi 외

We consider the networked multi-agent reinforcement learning (MARL) problem in a fully decentralized setting, where agents learn to coordinate to achieve the joint success. This problem is widely encountered in many area…

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Policy Gradients using Variational Quantum Circuits

2022-03-20 · André Sequeira, Luis Paulo Santos, Luís Soares Barbosa

Variational Quantum Circuits are being used as versatile Quantum Machine Learning models. Some empirical results exhibit an advantage in supervised and generative learning tasks. However, when applied to Reinforcement Le…

Benchmarking Quantum Machine Learning reinforcement-learning Reinforcement Learning+1

Diffusion-based Reinforcement Learning via Q-weighted Variational Policy Optimization

2024-05-25 · Shutong Ding, Ke Hu, Zhenhao Zhang, Kan Ren 외

Diffusion models have garnered widespread attention in Reinforcement Learning (RL) for their powerful expressiveness and multimodality. It has been verified that utilizing diffusion policies can significantly improve the…

continuous-control Continuous Control MuJoCo Offline RL+3