garage.replay_buffer package

This public package contains the replay buffer primitives.

The replay buffer primitives can be used for RL algorithms.

class HerReplayBuffer(replay_k, reward_fun, **kwargs)

Bases: garage.replay_buffer.base.ReplayBuffer

This class implements HerReplayBuffer.

It constructs hindsight examples using future strategy.

sample(batch_size)

Sample a transition of batch_size.

class PathBuffer(capacity_in_transitions)

Bases: object

A replay buffer that stores and can sample whole paths.

This buffer only stores valid steps, and doesn’t require paths to have a maximum length. :param capacity_in_steps: total memory allocated for the buffer :type capacity_in_steps: int

add_path(path)

Add a path to the buffer.

Parameters:path (dict) – A dict of array of shape (path_len, flat_dim)

sample_path()

Sample a single path from the buffer.

Returns:A dict of arrays of shape (path_len, flat_dim)

sample_transitions(batch_size)

Sample a batch of transitions from the buffer.

Returns:A dict of arrays of shape (batch_size, flat_dim)

class SimpleReplayBuffer(env_spec, size_in_transitions, time_horizon)

Bases: garage.replay_buffer.base.ReplayBuffer

This class implements SimpleReplayBuffer.

It uses random batch sample to minimize correlations between samples.

sample(batch_size)

Sample a transition of batch_size.

Submodules

• garage.replay_buffer.base module
• garage.replay_buffer.her_replay_buffer module
• garage.replay_buffer.path_buffer module
• garage.replay_buffer.simple_replay_buffer module