cntk.contrib.deeprl.agent.random_agent module

Baseline agent that selects action uniformly randomly.

class RandomAgent(o_space, a_space)

Bases: cntk.contrib.deeprl.agent.agent.AgentBaseClass

Agent that selects action uniformly randomly.

end(reward, next_state)

Last observed reward/state of the episode (which then terminates).

save(filename)

Save best model to file.

save_parameter_settings(filename)

Save parameter settings to file.

set_as_best_model()

Copy current model to best model.

start(state)

Start a new episode.

step(reward, next_state)

Observe one transition and choose an action.