Module: tf_agents.replay_buffers
Stay organized with collections
Save and categorize content based on your preferences.
Replay Buffers Module.
Modules
py_hashed_replay_buffer
module: Uniform replay buffer in Python with compressed storage.
py_uniform_replay_buffer
module: Uniform replay buffer in Python.
replay_buffer
module: TF-Agents Replay Buffer API.
reverb_replay_buffer
module: Reverb as a TF-Agents replay buffer.
reverb_utils
module: Utilities for working with a reverb replay buffer.
table
module: A tensorflow table stored in tf.Variables.
tf_uniform_replay_buffer
module: A batched replay buffer of nests of Tensors which can be sampled uniformly.
Classes
class ReverbAddEpisodeObserver
: Observer for writing episodes to Reverb.
class ReverbAddTrajectoryObserver
: Stateful observer for writing fixed length trajectories to Reverb.
class ReverbReplayBuffer
: Reverb ReplayBuffer exposed as a TF-Agents replay buffer.
class TFUniformReplayBuffer
: A TFUniformReplayBuffer with batched adds and uniform sampling.
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2024-04-26 UTC.
[null,null,["Last updated 2024-04-26 UTC."],[],[],null,["# Module: tf_agents.replay_buffers\n\n\u003cbr /\u003e\n\n|-----------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/agents/blob/v0.19.0/tf_agents/replay_buffers/__init__.py) |\n\nReplay Buffers Module.\n\nModules\n-------\n\n[`py_hashed_replay_buffer`](../tf_agents/replay_buffers/py_hashed_replay_buffer) module: Uniform replay buffer in Python with compressed storage.\n\n[`py_uniform_replay_buffer`](../tf_agents/replay_buffers/py_uniform_replay_buffer) module: Uniform replay buffer in Python.\n\n[`replay_buffer`](../tf_agents/replay_buffers/replay_buffer) module: TF-Agents Replay Buffer API.\n\n[`reverb_replay_buffer`](../tf_agents/replay_buffers/reverb_replay_buffer) module: Reverb as a TF-Agents replay buffer.\n\n[`reverb_utils`](../tf_agents/replay_buffers/reverb_utils) module: Utilities for working with a reverb replay buffer.\n\n[`table`](../tf_agents/replay_buffers/table) module: A tensorflow table stored in tf.Variables.\n\n[`tf_uniform_replay_buffer`](../tf_agents/replay_buffers/tf_uniform_replay_buffer) module: A batched replay buffer of nests of Tensors which can be sampled uniformly.\n\nClasses\n-------\n\n[`class ReverbAddEpisodeObserver`](../tf_agents/replay_buffers/ReverbAddEpisodeObserver): Observer for writing episodes to Reverb.\n\n[`class ReverbAddTrajectoryObserver`](../tf_agents/replay_buffers/ReverbAddTrajectoryObserver): Stateful observer for writing fixed length trajectories to Reverb.\n\n[`class ReverbReplayBuffer`](../tf_agents/replay_buffers/ReverbReplayBuffer): Reverb ReplayBuffer exposed as a TF-Agents replay buffer.\n\n[`class TFUniformReplayBuffer`](../tf_agents/replay_buffers/TFUniformReplayBuffer): A TFUniformReplayBuffer with batched adds and uniform sampling."]]