| exp_config = { | |
| 'main_config': { | |
| 'exp_name': 'TicTacToe-play-with-bot-GumbelMuZero', | |
| 'seed': 0, | |
| 'env': { | |
| 'env_id': 'TicTacToe-play-with-bot', | |
| 'battle_mode': 'play_with_bot_mode', | |
| 'collector_env_num': 8, | |
| 'evaluator_env_num': 5, | |
| 'n_evaluator_episode': 5, | |
| 'manager': { | |
| 'shared_memory': False | |
| } | |
| }, | |
| 'policy': { | |
| 'on_policy': False, | |
| 'cuda': True, | |
| 'multi_gpu': False, | |
| 'bp_update_sync': True, | |
| 'traj_len_inf': False, | |
| 'model': { | |
| 'observation_shape': [3, 3, 3], | |
| 'action_space_size': 9, | |
| 'image_channel': 3, | |
| 'num_res_blocks': 1, | |
| 'num_channels': 16, | |
| 'fc_reward_layers': [8], | |
| 'fc_value_layers': [8], | |
| 'fc_policy_layers': [8], | |
| 'support_scale': 10, | |
| 'reward_support_size': 21, | |
| 'value_support_size': 21 | |
| }, | |
| 'use_rnd_model': False, | |
| 'sampled_algo': False, | |
| 'gumbel_algo': True, | |
| 'mcts_ctree': True, | |
| 'collector_env_num': 8, | |
| 'evaluator_env_num': 5, | |
| 'env_type': 'board_games', | |
| 'action_type': 'varied_action_space', | |
| 'battle_mode': 'play_with_bot_mode', | |
| 'monitor_extra_statistics': True, | |
| 'game_segment_length': 5, | |
| 'transform2string': False, | |
| 'gray_scale': False, | |
| 'use_augmentation': False, | |
| 'augmentation': ['shift', 'intensity'], | |
| 'ignore_done': False, | |
| 'update_per_collect': 50, | |
| 'model_update_ratio': 0.1, | |
| 'batch_size': 256, | |
| 'optim_type': 'Adam', | |
| 'learning_rate': 0.003, | |
| 'target_update_freq': 100, | |
| 'target_update_freq_for_intrinsic_reward': 1000, | |
| 'weight_decay': 0.0001, | |
| 'momentum': 0.9, | |
| 'grad_clip_value': 0.5, | |
| 'n_episode': 8, | |
| 'num_simulations': 30, | |
| 'discount_factor': 1, | |
| 'td_steps': 9, | |
| 'num_unroll_steps': 3, | |
| 'reward_loss_weight': 1, | |
| 'value_loss_weight': 0.25, | |
| 'policy_loss_weight': 1, | |
| 'policy_entropy_loss_weight': 0, | |
| 'ssl_loss_weight': 0, | |
| 'lr_piecewise_constant_decay': False, | |
| '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': 'GumbelMuZeroPolicyDict', | |
| 'max_num_considered_actions': 3, | |
| 'reanalyze_ratio': 0.0, | |
| 'eval_freq': 2000, | |
| 'replay_buffer_size': 10000 | |
| }, | |
| 'wandb_logger': { | |
| 'gradient_logger': False, | |
| 'video_logger': False, | |
| 'plot_logger': False, | |
| 'action_logger': False, | |
| 'return_logger': False | |
| } | |
| }, | |
| 'create_config': { | |
| 'env': { | |
| 'type': 'tictactoe', | |
| 'import_names': ['zoo.board_games.tictactoe.envs.tictactoe_env'] | |
| }, | |
| 'env_manager': { | |
| 'type': 'subprocess' | |
| }, | |
| 'policy': { | |
| 'type': 'gumbel_muzero', | |
| 'import_names': ['lzero.policy.gumbel_muzero'] | |
| } | |
| } | |
| } | |