DeepAI AI Chat
Log In Sign Up

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

by   Yue Jin, et al.

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 of such information is often done in an implicit and uninterpretable manner, or explicitly with cost functions not able to reflect the relationship between information compression and utility in representation. In this paper, we present Information-Bottleneck-based Other agents' behavior Representation learning for Multi-agent reinforcement learning (IBORM) to explicitly seek low-dimensional mapping encoder through which a compact and informative representation relevant to other agents' behaviors is established. IBORM leverages the information bottleneck principle to compress observation information, while retaining sufficient information relevant to other agents' behaviors used for cooperation decision. Empirical results have demonstrated that IBORM delivers the fastest convergence rate and the best performance of the learned policies, as compared with implicit behavior representation learning and explicit behavior representation learning without explicitly considering information compression and utility.


page 1

page 2

page 3

page 4


HAMMER: Multi-Level Coordination of Reinforcement Learning Agents via Learned Messaging

Cooperative multi-agent reinforcement learning (MARL) has achieved signi...

Deep Reinforcement Learning for Multi-Agent Interaction

The development of autonomous agents which can interact with other agent...

SEA: A Spatially Explicit Architecture for Multi-Agent Reinforcement Learning

Spatial information is essential in various fields. How to explicitly mo...

Increasing the Efficiency of Policy Learning for Autonomous Vehicles by Multi-Task Representation Learning

Driving in a dynamic, multi-agent, and complex urban environment is a di...

Improved Structural Discovery and Representation Learning of Multi-Agent Data

Central to all machine learning algorithms is data representation. For m...

Parameter Sharing Reinforcement Learning Architecture for Multi Agent Driving Behaviors

Multi-agent learning provides a potential framework for learning and sim...

Learning Representations in Reinforcement Learning:An Information Bottleneck Approach

The information bottleneck principle is an elegant and useful approach t...