ray.rllib.algorithms.algorithm.Algorithm.env_runner_group#

Algorithm.env_runner_group: EnvRunnerGroup | None = None#

The EnvRunnerGroup of the Algorithm. An EnvRunnerGroup is composed of a single local EnvRunner (see: self.env_runner), serving as the reference copy of the models to be trained and optionally one or more remote EnvRunners used to generate training samples from the RL environment, in parallel. EnvRunnerGroup is fault-tolerant and elastic. It tracks health states for all the managed remote EnvRunner actors. As a result, Algorithm should never access the underlying actor handles directly. Instead, always access them via all the foreach APIs with assigned IDs of the underlying EnvRunners.