loading page

Decentralized Multi-Agent Advantage Actor-Critic
  • Scott Barnes
Scott Barnes
The George Washington University

Corresponding Author:[email protected]

Author Profile

Abstract

We present a decentralized advantage actor-critic algorithm that utilizes learning agents in parallel environments with synchronous gradient descent. This approach decorrelates agents' experiences, stabilizing observations and eliminating the need for a replay buffer, requires no knowledge of the other agents' internal state during training or execution, and runs on a single multi-core CPU.