Asynchronous Actor-Critic for Multi-Agent Reinforcement Learning. (arXiv:2209.10113v2 [cs.LG] UPDATED)

Synchronizing decisions across multiple agents in realistic settings is
problematic since it requires agents to wait for other agents to terminate and
communicate about termination reliably. Ideally, agents should learn and
execute asynchronously instead. Such asynchronous methods also allow temporally
extended actions that can take different amounts of time based on the situation
and action executed. Unfortunately, current policy gradient methods are not
applicable in asynchronous settings, as they assume that agents synchronously
reason about action selection at every time …

actor-critic arxiv asynchronous reinforcement reinforcement learning