Reliably Re-Acting to Partner's Actions with the Social Intrinsic Motivation of Transfer Empowerment

03/07/2022

∙

We consider multi-agent reinforcement learning (MARL) for cooperative communication and coordination tasks. MARL agents can be brittle because they can overfit their training partners' policies. This overfitting can produce agents that adopt policies that act under the expectation that other agents will act in a certain way rather than react to their actions. Our objective is to bias the learning process towards finding reactive strategies towards other agents' behaviors. Our method, transfer empowerment, measures the potential influence between agents' actions. Results from three simulated cooperation scenarios support our hypothesis that transfer empowerment improves MARL performance. We discuss how transfer empowerment could be a useful principle to guide multi-agent coordination by ensuring reactiveness to one's partner.

READ FULL TEXT

Reliably Re-Acting to Partner's Actions with the Social Intrinsic Motivation of Transfer Empowerment

Robust Multi-Agent Reinforcement Learning with Social Empowerment for Coordination and Communication

Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning

Influence-based Reinforcement Learning for Intrinsically-motivated Agents

TransfQMix: Transformers for Leveraging the Graph Structure of Multi-Agent Reinforcement Learning Problems

A Dataset Schema for Cooperative Learning from Demonstration in Multi-robots Systems

Evolving Dyadic Strategies for a Cooperative Physical Task

Intrinsic Social Motivation via Causal Influence in Multi-Agent RL

Reliably Re-Acting to Partner's Actions with the Social Intrinsic Motivation of Transfer Empowerment

Related Research

Robust Multi-Agent Reinforcement Learning with Social Empowerment for Coordination and Communication

Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning

Influence-based Reinforcement Learning for Intrinsically-motivated Agents

TransfQMix: Transformers for Leveraging the Graph Structure of Multi-Agent Reinforcement Learning Problems

A Dataset Schema for Cooperative Learning from Demonstration in Multi-robots Systems

Evolving Dyadic Strategies for a Cooperative Physical Task

Intrinsic Social Motivation via Causal Influence in Multi-Agent RL