| exp_config = { |
| 'main_config': { |
| 'exp_name': 'MsPacmanNoFrameskip-v4-EfficientZero', |
| 'seed': 0, |
| 'env': { |
| 'env_id': 'MsPacmanNoFrameskip-v4', |
| 'env_name': 'MsPacmanNoFrameskip-v4', |
| 'obs_shape': [4, 96, 96], |
| 'collector_env_num': 8, |
| 'evaluator_env_num': 3, |
| 'n_evaluator_episode': 3, |
| 'manager': { |
| 'shared_memory': False |
| } |
| }, |
| 'policy': { |
| 'on_policy': False, |
| 'cuda': True, |
| 'multi_gpu': False, |
| 'bp_update_sync': True, |
| 'traj_len_inf': False, |
| 'model': { |
| 'observation_shape': [4, 96, 96], |
| 'frame_stack_num': 4, |
| 'action_space_size': 9, |
| 'downsample': True, |
| 'discrete_action_encoding_type': 'one_hot', |
| 'norm_type': 'BN' |
| }, |
| 'use_rnd_model': False, |
| 'sampled_algo': False, |
| 'gumbel_algo': False, |
| 'mcts_ctree': True, |
| 'collector_env_num': 8, |
| 'evaluator_env_num': 3, |
| 'env_type': 'not_board_games', |
| 'action_type': 'fixed_action_space', |
| 'battle_mode': 'play_with_bot_mode', |
| 'monitor_extra_statistics': True, |
| 'game_segment_length': 400, |
| 'transform2string': False, |
| 'gray_scale': False, |
| 'use_augmentation': True, |
| 'augmentation': ['shift', 'intensity'], |
| 'ignore_done': False, |
| 'update_per_collect': 1000, |
| 'model_update_ratio': 0.1, |
| 'batch_size': 256, |
| 'optim_type': 'SGD', |
| 'learning_rate': 0.2, |
| 'target_update_freq': 100, |
| 'target_update_freq_for_intrinsic_reward': 1000, |
| 'weight_decay': 0.0001, |
| 'momentum': 0.9, |
| 'grad_clip_value': 10, |
| 'n_episode': 8, |
| 'num_simulations': 50, |
| 'discount_factor': 0.997, |
| 'td_steps': 5, |
| 'num_unroll_steps': 5, |
| 'reward_loss_weight': 1, |
| 'value_loss_weight': 0.25, |
| 'policy_loss_weight': 1, |
| 'policy_entropy_loss_weight': 0, |
| 'ssl_loss_weight': 2, |
| 'lr_piecewise_constant_decay': True, |
| 'threshold_training_steps_for_final_lr': 50000, |
| 'manual_temperature_decay': False, |
| 'threshold_training_steps_for_final_temperature': 100000, |
| 'fixed_temperature_value': 0.25, |
| 'use_ture_chance_label_in_chance_encoder': False, |
| 'use_priority': True, |
| 'priority_prob_alpha': 0.6, |
| 'priority_prob_beta': 0.4, |
| 'root_dirichlet_alpha': 0.3, |
| 'root_noise_weight': 0.25, |
| 'random_collect_episode_num': 0, |
| 'eps': { |
| 'eps_greedy_exploration_in_collect': False, |
| 'type': 'linear', |
| 'start': 1.0, |
| 'end': 0.05, |
| 'decay': 100000 |
| }, |
| 'cfg_type': 'EfficientZeroPolicyDict', |
| 'lstm_horizon_len': 5, |
| 'reanalyze_ratio': 0.0, |
| 'eval_freq': 2000, |
| 'replay_buffer_size': 1000000 |
| }, |
| 'wandb_logger': { |
| 'gradient_logger': False, |
| 'video_logger': False, |
| 'plot_logger': False, |
| 'action_logger': False, |
| 'return_logger': False |
| } |
| }, |
| 'create_config': { |
| 'env': { |
| 'type': 'atari_lightzero', |
| 'import_names': ['zoo.atari.envs.atari_lightzero_env'] |
| }, |
| 'env_manager': { |
| 'type': 'subprocess' |
| }, |
| 'policy': { |
| 'type': 'efficientzero', |
| 'import_names': ['lzero.policy.efficientzero'] |
| } |
| } |
| } |
|
|
