low_level_policy_main module¶
-
class
low_level_policy_main.
ManeuverEvaluateCallback
(maneuver)¶ Bases:
rl.callbacks.Callback
-
on_episode_end
(episode, logs={})¶ Called at end of each episode
-
on_train_end
(logs=None)¶
-
-
low_level_policy_main.
evaluate_low_level_policy
(maneuver, pretrained=False, nb_episodes_for_eval=100)¶
-
low_level_policy_main.
low_level_policy_testing
(maneuver, pretrained=False, visualize=True, nb_episodes_for_test=20)¶
-
low_level_policy_main.
low_level_policy_training
(maneuver, nb_steps, RL_method='DDPG', load_weights=False, training=True, testing=True, visualize=False, nb_episodes_for_test=10, tensorboard=False, without_ltl=False)¶ Do RL of the low-level policy of the given maneuver and test it.
Parameters: - maneuver – the name of the maneuver defined in config.json (e.g., ‘default’).
- nb_steps – the number of steps to perform RL.
- RL_method – either DDPG or PPO2.
- load_weights – True if the pre-learned NN weights are loaded (for initializations of NNs).
- training – True to enable training.
- testing – True to enable testing.
- visualize – True to see the graphical outputs during training.
- nb_episodes_for_test – the number of episodes for testing.