garage.np.algos.cem module¶
Cross Entropy Method.
-
class
CEM
(env_spec, policy, baseline, n_samples, discount=0.99, max_path_length=500, init_std=1, best_frac=0.05, extra_std=1.0, extra_decay_time=100)[source]¶ Bases:
garage.np.algos.rl_algorithm.RLAlgorithm
Cross Entropy Method.
CEM works by iteratively optimizing a gaussian distribution of policy.
In each epoch, CEM does the following: 1. Sample n_samples policies from a gaussian distribution of
mean cur_mean and std cur_std.- Do rollouts for each policy.
- Update cur_mean and cur_std by doing Maximum Likelihood Estimation over the n_best top policies in terms of return.
Parameters: - env_spec (garage.envs.EnvSpec) – Environment specification.
- policy (garage.np.policies.Policy) – Action policy.
- baseline (garage.np.baselines.Baseline) – Baseline for GAE (Generalized Advantage Estimation).
- n_samples (int) – Number of policies sampled in one epoch.
- discount (float) – Environment reward discount.
- max_path_length (int) – Maximum length of a single rollout.
- best_frac (float) – The best fraction.
- init_std (float) – Initial std for policy param distribution.
- extra_std (float) – Decaying std added to param distribution.
- extra_decay_time (float) – Epochs that it takes to decay extra std.
-
train
(runner)[source]¶ Initialize variables and start training.
Parameters: runner (LocalRunner) – LocalRunner is passed to give algorithm the access to runner.step_epochs(), which provides services such as snapshotting and sampler control. Returns: The average return in last epoch cycle. Return type: float