garage.sampler.base module

class BaseSampler(algo, env)[source]

Bases: garage.sampler.base.Sampler

Base class for sampler.

Parameters:
  • algo (garage.np.algos.RLAlgorithm) – The algorithm.
  • env (gym.Env) – The environment.
class Sampler[source]

Bases: abc.ABC

obtain_samples(itr)[source]

Collect samples for the given iteration number.

Parameters:itr (int) – Iteration number.
Returns:A list of paths.
Return type:list[dict]
shutdown_worker()[source]

Terminate workers if necessary.

start_worker()[source]

Initialize the sampler,

e.g. launching parallel workers if necessary.