cntk.contrib.deeprl.agent.tabular_qlearning module

Tabular Q-learning.

class TabularQLearning(cfg_filename, o_space, a_space)[source]

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

Q-learning agent with tabular representation.

end(reward, next_state)[source]

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

enter_evaluation()[source]

Setup before evaluation.

save(filename)[source]

Save best model to file.

save_parameter_settings(filename)[source]

Save parameter settings to file.

set_as_best_model()[source]

Copy current model to best model.

start(state)[source]

Start a new episode.

step(reward, next_state)[source]

Observe one transition and choose an action.