MSRL: Distributed Reinforcement Learning with Dataflow Fragments. (arXiv:2210.00882v2 [cs.LG] UPDATED)

Reinforcement learning (RL) trains many agents, which is resource-intensive
and must scale to large GPU clusters. Different RL training algorithms offer
different opportunities for distributing and parallelising the computation.
Yet, current distributed RL systems tie the definition of RL algorithms to
their distributed execution: they hard-code particular distribution strategies
and only accelerate specific parts of the computation (e.g. policy network
updates) on GPU workers. Fundamentally, current systems lack abstractions that
decouple RL algorithms from their execution.

We describe MindSpore Reinforcement …

arxiv dataflow distributed reinforcement reinforcement learning