garage.np.algos.nop

NOP (no optimization performed) policy search algorithm.

class NOP

Bases: garage.np.algos.rl_algorithm.RLAlgorithm

Inheritance diagram of garage.np.algos.nop.NOP

NOP (no optimization performed) policy search algorithm.

init_opt(self)

Initialize the optimization procedure.

optimize_policy(self, paths)

Optimize the policy using the samples.

Parameters

paths (list[dict]) – A list of collected paths.

train(self, trainer)

Obtain samplers and start actual training for each epoch.

Parameters

trainer (Trainer) – Trainer is passed to give algorithm the access to trainer.step_epochs(), which provides services such as snapshotting and sampler control.