paper-with-me

홈 › Papers

MACRPO: Multi-Agent Cooperative Recurrent Policy Optimization

2021-09-02 · Eshagh Kargar, Ville Kyrki

This work considers the problem of learning cooperative policies in multi-agent settings with partially observable and non-stationary environments without a communication channel. We focus on improving information sharing between agents and propose a new multi-agent actor-critic method called \textit{Multi-Agent Cooperative Recurrent Proximal Policy Optimization} (MACRPO). We propose two novel ways of integrating information across agents and time in MACRPO: First, we use a recurrent layer in critic's network architecture and propose a new framework to use a meta-trajectory to train the recurrent layer. This allows the network to learn the cooperation and dynamics of interactions between agents, and also handle partial observability. Second, we propose a new advantage function that incorporates other agents' rewards and value functions. We evaluate our algorithm on three challenging multi-agent environments with continuous and discrete action spaces, Deepdrive-Zero, Multi-Walker, and Particle environment. We compare the results with several ablations and state-of-the-art multi-agent algorithms such as QMIX and MADDPG and also single-agent methods with shared parameters between agents such as IMPALA and APEX. The results show superior performance against other algorithms. The code is available online at https://github.com/kargarisaac/macrpo.

📄 PDF Abstract BibTeX arXiv:2109.00882

Code (1)

kargarisaac/macrpo 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Tanh Activation 설명 없음
Sigmoid Activation 설명 없음
Residual Connection 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
V-trace V-trace is an off-policy actor-critic reinforcement learning algorithm that helps tackle the lag between when actions are generated by the actors and when the learner…
RMSProp RMSProp is an unpublished adaptive learning rate optimizer proposed by Geoff Hinton. The motivation…

Similar Papers 제목 키워드 기반

Probabilistic Verification of Recurrent Neural Networks for Single and Multi-Agent Reinforcement Learning

2026-05-14 · Luca Marzari, Enrico Marchesini arxiv

History-dependent policies induced by recurrent neural networks (RNNs) rely on latent hidden state dynamics, making verification in partially observable reinforcement learning (RL) challenging. Existing RNN verification …

Multi-agent Reinforcement Learning

M$^{2}$GRPO: Mamba-based Multi-Agent Group Relative Policy Optimization for Biomimetic Underwater Robots Pursuit

2026-04-21 · Yukai Feng, Zhiheng Wu, Zhengxing Wu, Junwen Gu 외 arxiv

Traditional policy learning methods in cooperative pursuit face fundamental challenges in biomimetic underwater robots, where long-horizon decision making, partial observability, and inter-robot coordination require both…

Decision Making

Multi-Scenario Combination Based on Multi-Agent Reinforcement Learning to Optimize the Advertising Recommendation System

2024-07-03 · Yang Zhao, Chang Zhou, Jin Cao, Yi Zhao 외

This paper explores multi-scenario optimization on large platforms using multi-agent reinforcement learning (MARL). We address this by treating scenarios like search, recommendation, and advertising as a cooperative, par…

Multi-agent Reinforcement Learning

Cooperative and Competitive Biases for Multi-Agent Reinforcement Learning

2021-01-18 · Heechang Ryu, Hayong Shin, Jinkyoo Park

Training a multi-agent reinforcement learning (MARL) algorithm is more challenging than training a single-agent reinforcement learning algorithm, because the result of a multi-agent task strongly depends on the complex i…

Multi-agent Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Developing cooperative policies for multi-stage tasks

2020-07-01 · Jordan Erskine, Chris Lehnert

This paper proposes the Cooperative Soft Actor Critic (CSAC) method of enabling consecutive reinforcement learning agents to cooperatively solve a long time horizon multi-stage task. This method is achieved by modifying …

Reinforcement Learning (RL)