garage.sampler.is_sampler module¶
-
class
ISSampler
(algo, env, n_backtrack='all', n_is_pretrain=0, init_is=0, skip_is_itrs=False, hist_variance_penalty=0.0, max_is_ratio=0, ess_threshold=0, randomize_draw=False)[source]¶ Bases:
garage.sampler.batch_sampler.BatchSampler
Sampler which alternates between live sampling iterations using BatchSampler and importance sampling iterations.
Parameters: - algo (garage.np.algos.RLAlgorithm) – An algorithm instance.
- env (garage.envs.GarageEnv) – An environement instance.
- n_backtrack (str/int) – Number of past policies to update from
- n_is_pretrain (int) – Number of importance sampling iterations to perform in beginning of training
- init_is (bool) – Set initial iteration (after pretrain) an importance sampling iteration.
- skip_is_itrs (bool) – Do not do any importance sampling iterations (after pretrain).
- hist_variance_penalty (int) – Penalize variance of historical policy.
- max_is_ratio (int) – Maximum allowed importance sampling ratio.
- ess_threshold (int) – Minimum effective sample size required.
- randomize_draw (bool) – Whether to randomize important samples.
-
history
¶ History of policies that have interacted with the environment and the data from interaction episode(s)