# Policy Distillation and Value Matching in Multiagent Reinforcement Learning

## TL;DR

This paper introduces a multiagent actor-critic method that uses policy distillation and value matching to improve learning efficiency and performance in multiagent reinforcement learning tasks, especially in high-dimensional spaces.

## Contribution

It proposes a novel approach combining policy distillation and value matching for homogeneous agents, enhancing multiagent RL beyond existing methods.

## Key findings

- Outperforms policy distillation alone in experiments.
- Enables further learning in discrete and continuous action spaces.
- Addresses the curse of dimensionality in multiagent RL.

## Abstract

Multiagent reinforcement learning algorithms (MARL) have been demonstrated on complex tasks that require the coordination of a team of multiple agents to complete. Existing works have focused on sharing information between agents via centralized critics to stabilize learning or through communication to increase performance, but do not generally look at how information can be shared between agents to address the curse of dimensionality in MARL. We posit that a multiagent problem can be decomposed into a multi-task problem where each agent explores a subset of the state space instead of exploring the entire state space. This paper introduces a multiagent actor-critic algorithm and method for combining knowledge from homogeneous agents through distillation and value-matching that outperforms policy distillation alone and allows further learning in both discrete and continuous action spaces.