Representation Learning For Efficient Deep Multi-Agent Reinforcement Learning

2024-06-05 · Dom Huh, Prasant Mohapatra

Sample efficiency remains a key challenge in multi-agent reinforcement learning (MARL). A promising approach is to learn a meaningful latent representation space through auxiliary learning objectives alongside the MARL objective to aid in learning a successful control policy. In our work, we present MAPO-LSO (Multi-Agent Policy Optimization with Latent Space Optimization) which applies a form of comprehensive representation learning devised to supplement MARL training. Specifically, MAPO-LSO proposes a multi-agent extension of transition dynamics reconstruction and self-predictive learning that constructs a latent state optimization scheme that can be trivially extended to current state-of-the-art MARL algorithms. Empirical results demonstrate MAPO-LSO to show notable improvements in sample efficiency and learning performance compared to its vanilla MARL counterpart without any additional MARL hyperparameter tuning on a diverse suite of MARL tasks.

📄 PDF Abstract BibTeX arXiv:2406.02890

Code (0)

등록된 구현이 없습니다.

Tasks

Auxiliary LearningMulti-agent Reinforcement Learning reinforcement-learning Reinforcement Learning Representation Learning

How to Sense the World: Leveraging Hierarchy in Multimodal Perception for Robust Reinforcement Learning Agents

2021-10-07 · Miguel Vasco, Hang Yin, Francisco S. Melo, Ana Paiva

This work addresses the problem of sensing the world: how to learn a multimodal representation of a reinforcement learning agent's environment that allows the execution of tasks under incomplete perceptual conditions. To…

Atari Games Deep Reinforcement Learning reinforcement-learning Reinforcement Learning+2

Information-Bottleneck-Based Behavior Representation Learning for Multi-agent Reinforcement learning

2021-09-29 · Yue Jin, Shuangqing Wei, Jian Yuan, Xudong Zhang

In multi-agent deep reinforcement learning, extracting sufficient and compact information of other agents is critical to attain efficient convergence and scalability of an algorithm. In canonical frameworks, distilling o…

Deep Reinforcement Learning Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning+2

MAGNet: Multi-agent Graph Network for Deep Multi-agent Reinforcement Learning

2020-12-17 · Aleksandra Malysheva, Daniel Kudenko, Aleksei Shpilman

Over recent years, deep reinforcement learning has shown strong successes in complex single-agent tasks, and more recently this approach has also been applied to multi-agent domains. In this paper, we propose a novel app…

Deep Reinforcement Learning Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning+1

Reinforcement Learning under a Multi-agent Predictive State Representation Model: Method and Theory

2021-09-29 · ICLR 2022 4 · Zhi Zhang, Zhuoran Yang, Han Liu, Pratap Tokekar 외

This paper proposes a new algorithm for learning the optimal policies under a novel multi-agent predictive state representation reinforcement learning model. Compared to the state-of-the-art methods, the most striking fe…

reinforcement-learning Reinforcement Learning (RL)

Celebrating Diversity in Shared Multi-Agent Reinforcement Learning

2021-06-04 · NeurIPS 2021 12 · Chenghao Li, Tonghan Wang, Chengjie WU, Qianchuan Zhao 외

Recently, deep multi-agent reinforcement learning (MARL) has shown the promise to solve complex cooperative tasks. Its success is partly because of parameter sharing among agents. However, such sharing may lead agents to…

Diversity Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning+3