Multi-Agent Actor-Critic with Hierarchical Graph Attention Network

2019-09-27 · Heechang Ryu, Hayong Shin, Jinkyoo Park

Most previous studies on multi-agent reinforcement learning focus on deriving decentralized and cooperative policies to maximize a common reward and rarely consider the transferability of trained policies to new tasks. This prevents such policies from being applied to more complex multi-agent tasks. To resolve these limitations, we propose a model that conducts both representation learning for multiple agents using hierarchical graph attention network and policy learning using multi-agent actor-critic. The hierarchical graph attention network is specially designed to model the hierarchical relationships among multiple agents that either cooperate or compete with each other to derive more advanced strategic policies. Two attention networks, the inter-agent and inter-group attention layers, are used to effectively model individual and group level interactions, respectively. The two attention networks have been proven to facilitate the transfer of learned policies to new tasks with different agent compositions and allow one to interpret the learned strategies. Empirically, we demonstrate that the proposed model outperforms existing methods in several mixed cooperative and competitive tasks.

📄 PDF Abstract BibTeX arXiv:1909.12557

Code (0)

등록된 구현이 없습니다.

Tasks

Graph AttentionMulti-agent Reinforcement Learning Reinforcement Learning Representation Learning

Natural Actor-Critic Converges Globally for Hierarchical Linear Quadratic Regulator

2019-12-14 · Yuwei Luo, Zhuoran Yang, Zhaoran Wang, Mladen Kolar

Multi-agent reinforcement learning has been successfully applied to a number of challenging problems. Despite these empirical successes, theoretical understanding of different algorithms is lacking, primarily due to the …

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

Soft Hierarchical Graph Recurrent Networks for Many-Agent Partially Observable Environments

2021-09-05 · Zhenhui Ye, Xiaohong Jiang, Guanghua Song, Bowei Yang

The recent progress in multi-agent deep reinforcement learning(MADRL) makes it more practical in real-world tasks, but its relatively poor scalability and the partially observable constraints raise challenges to its perf…

Deep Reinforcement Learning Graph Attention

Hierarchical Reinforcement Learning for Zero-shot Generalization with Subtask Dependencies

2018-07-19 · NeurIPS 2018 12 · Sungryull Sohn, Junhyuk Oh, Honglak Lee

We introduce a new RL problem where the agent is required to generalize to a previously-unseen environment characterized by a subtask graph which describes a set of subtasks and their dependencies. Unlike existing hierar…

Hierarchical Reinforcement Learning Network Embedding reinforcement-learning Reinforcement Learning+2

Efficient Policy Generation in Multi-Agent Systems via Hypergraph Neural Network

2022-03-07 · Bin Zhang, Yunpeng Bai, Zhiwei Xu, Dapeng Li 외

The application of deep reinforcement learning in multi-agent systems introduces extra challenges. In a scenario with numerous agents, one of the most important concerns currently being addressed is how to develop suffic…

Decision Making Deep Reinforcement Learning Multi-agent Reinforcement Learning reinforcement-learning+3

Modelling Bounded Rationality in Multi-Agent Interactions by Generalized Recursive Reasoning

2019-01-26 · Ying Wen, Yaodong Yang, Rui Luo, Jun Wang

Though limited in real-world decision making, most multi-agent reinforcement learning (MARL) models assume perfectly rational agents -- a property hardly met due to individual's cognitive limitation and/or the tractabili…

Decision Making Multi-agent Reinforcement Learning Reinforcement Learning