metarl.np.algos.nop module

NOP (no optimization performed) policy search algorithm.

class NOP[source]

Bases: metarl.np.algos.rl_algorithm.RLAlgorithm

NOP (no optimization performed) policy search algorithm.

init_opt()[source]

Initialize the optimization procedure.

optimize_policy(paths)[source]

Optimize the policy using the samples.

Parameters:paths (list[dict]) – A list of collected paths.
train(runner)[source]

Obtain samplers and start actual training for each epoch.

Parameters:runner (LocalRunner) – LocalRunner is passed to give algorithm the access to runner.step_epochs(), which provides services such as snapshotting and sampler control.