| __init__(self) | train_policy_gradient.PolicyGradientTrainingNode | |
| training_node::TrainingNode.__init__(self, policy, actions, laser_sample_count, max_episode_length, learn_rate) | training_node.TrainingNode | |
| reinforcement_learning_node::ReinforcementLearningNode.__init__(self, actions, laser_sample_count) | reinforcement_learning_node.ReinforcementLearningNode | |
| action | training_node.TrainingNode | |
| actions | reinforcement_learning_node.ReinforcementLearningNode | |
| car_orientation | training_node.TrainingNode | |
| car_position | training_node.TrainingNode | |
| check_car_orientation(self) | training_node.TrainingNode | |
| convert_laser_message_to_tensor(self, message, use_device=True) | reinforcement_learning_node.ReinforcementLearningNode | |
| cumulative_reward | training_node.TrainingNode | |
| cumulative_reward_history | training_node.TrainingNode | |
| current_episode_rewards | train_policy_gradient.PolicyGradientTrainingNode | |
| drive_forward | training_node.TrainingNode | |
| drive_parameters_publisher | reinforcement_learning_node.ReinforcementLearningNode | |
| episode_count | training_node.TrainingNode | |
| episode_length | training_node.TrainingNode | |
| episode_length_history | training_node.TrainingNode | |
| episode_result_publisher | training_node.TrainingNode | |
| episode_start_time_real | training_node.TrainingNode | |
| episode_start_time_sim | training_node.TrainingNode | |
| get_episode_summary(self) | training_node.TrainingNode | |
| get_reward(self) | train_policy_gradient.PolicyGradientTrainingNode | |
| is_terminal_step | training_node.TrainingNode | |
| laser_sample_count | reinforcement_learning_node.ReinforcementLearningNode | |
| max_episode_length | training_node.TrainingNode | |
| net_output_debug_string | training_node.TrainingNode | |
| on_complete_episode(self) | train_policy_gradient.PolicyGradientTrainingNode | |
| on_complete_step(self, state, action, reward, next_state) | train_policy_gradient.PolicyGradientTrainingNode | |
| on_crash(self, _) | training_node.TrainingNode | |
| on_model_state_callback(self, message) | training_node.TrainingNode | |
| on_receive_laser_scan(self, message) | training_node.TrainingNode | |
| optimizer | training_node.TrainingNode | |
| perform_action(self, action_index) | reinforcement_learning_node.ReinforcementLearningNode | |
| policy | training_node.TrainingNode | |
| policy_history | train_policy_gradient.PolicyGradientTrainingNode | |
| scan_indices | reinforcement_learning_node.ReinforcementLearningNode | |
| select_action(self, state) | train_policy_gradient.PolicyGradientTrainingNode | |
| state | training_node.TrainingNode | |
| steps_with_wrong_orientation | training_node.TrainingNode | |
| total_step_count | training_node.TrainingNode | |
| update_policy(self) | train_policy_gradient.PolicyGradientTrainingNode | |
1.8.11 
