Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks

2018-12-23 · ICLR 2019 5 · Amanpreet Singh, Tushar Jain, Sainbayar Sukhbaatar

Learning when to communicate and doing that effectively is essential in multi-agent tasks. Recent works show that continuous communication allows efficient training with back-propagation in multi-agent scenarios, but have been restricted to fully-cooperative tasks. In this paper, we present Individualized Controlled Continuous Communication Model (IC3Net) which has better training efficiency than simple continuous communication model, and can be applied to semi-cooperative and competitive settings along with the cooperative settings. IC3Net controls continuous communication with a gating mechanism and uses individualized rewards foreach agent to gain better performance and scalability while fixing credit assignment issues. Using variety of tasks including StarCraft BroodWars explore and combat scenarios, we show that our network yields improved performance and convergence rates than the baselines as the scale increases. Our results convey that IC3Net agents learn when to communicate based on the scenario and profitability.

📄 PDF Abstract BibTeX arXiv:1812.09755

Code (3)

IC3Net/IC3Net 공식 구현 pytorch

RL-WFU/IC3Net-Highway pytorch

apsdehal/gym-starcraft

Tasks

Starcraft

Differential Privacy in Cooperative Multiagent Planning

2023-01-20 · Bo Chen, Calvin Hawkins, Mustafa O. Karabag, Cyrus Neary 외

Privacy-aware multiagent systems must protect agents' sensitive data while simultaneously ensuring that agents accomplish their shared objectives. Towards this goal, we propose a framework to privatize inter-agent commun…

Decision Making Sequential Decision Making

Weighted Double Deep Multiagent Reinforcement Learning in Stochastic Cooperative Environments

2018-02-23 · Yan Zheng, Jianye Hao, Zongzhang Zhang

Recently, multiagent deep reinforcement learning (DRL) has received increasingly wide attention. Existing multiagent DRL algorithms are inefficient when facing with the non-stationarity due to agents update their policie…

Deep Reinforcement Learning Q-Learning reinforcement-learning Reinforcement Learning+1

Hierarchical Deep Multiagent Reinforcement Learning with Temporal Abstraction

2018-09-25 · Hongyao Tang, Jianye Hao, Tangjie Lv, Yingfeng Chen 외

Multiagent reinforcement learning (MARL) is commonly considered to suffer from non-stationary environments and exponentially increasing policy space. It would be even more challenging when rewards are sparse and delayed …

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Agent Modeling as Auxiliary Task for Deep Reinforcement Learning

2019-07-22 · Pablo Hernandez-Leal, Bilal Kartal, Matthew E. Taylor

In this paper we explore how actor-critic methods in deep reinforcement learning, in particular Asynchronous Advantage Actor-Critic (A3C), can be extended with agent modeling. Inspired by recent works on representation l…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+1

A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning

2020-10-31 · Dong-Ki Kim, Miao Liu, Matthew Riemer, Chuangchuang Sun 외

A fundamental challenge in multiagent reinforcement learning is to learn beneficial behaviors in a shared environment with other simultaneously learning agents. In particular, each agent perceives the environment as effe…

reinforcement-learning Reinforcement Learning (RL)