Ray RLlib API# The Ray RLlib API reference documents RLlib’s public Python API. Each page below covers one group of APIs. Algorithm Configuration API Constructor Builder methods Properties Getter methods Public methods Configuration methods Algorithm-specific configuration classes Algorithms Building Custom Algorithm Classes Algorithm API Callback APIs Methods to implement for custom behavior RLlibCallback Callbacks invoked in Algorithm Callbacks invoked in EnvRunner Built-in callback classes Environments Env Vectorization External Envs Environment API Reference RLModule APIs RLModule specifications and configurations RLModule API MultiRLModule API Additional RLModule APIs Distribution API Base Distribution class LearnerGroup API Configuring a LearnerGroup and Learner actors Constructing a LearnerGroup Learner API Constructing a Learner Implementing a custom RLModule to fit a Learner Performing updates Computing losses Configuring optimizers Gradient computation Saving and restoring Adding and removing modules Offline RL API Configuring Offline RL Configuring Offline Recording EnvRunners Constructing a Recording EnvRunner Constructing OfflineData Sampling from Offline Data Constructing an OfflinePreLearner Transforming Data with an OfflinePreLearner ConnectorV2 API rllib.connectors.connector_v2.ConnectorV2 rllib.connectors.connector_pipeline_v2.ConnectorPipelineV2 Observation preprocessors rllib.connectors.env_to_module.observation_preprocessor.SingleAgentObservationPreprocessor rllib.connectors.env_to_module.observation_preprocessor.MultiAgentObservationPreprocessor Replay Buffer API Replay Buffer Base Classes Public Methods Multi Agent Buffers Utility Methods RLlib Utilities MetricsLogger API Scheduler API Framework Utilities API stability annotations Checkpoint utilities