| exp_config = { | |
| 'env': { | |
| 'manager': { | |
| 'episode_num': float("inf"), | |
| 'max_retry': 1, | |
| 'retry_type': 'reset', | |
| 'auto_reset': True, | |
| 'step_timeout': None, | |
| 'reset_timeout': None, | |
| 'retry_waiting_time': 0.1, | |
| 'cfg_type': 'BaseEnvManagerDict' | |
| }, | |
| 'stop_value': 10000000000, | |
| 'n_evaluator_episode': 8, | |
| 'collector_env_num': 16, | |
| 'evaluator_env_num': 8, | |
| 'env_id': 'QbertNoFrameskip-v4', | |
| 'frame_stack': 4 | |
| }, | |
| 'policy': { | |
| 'model': { | |
| 'obs_shape': [4, 84, 84], | |
| 'action_shape': 6, | |
| 'encoder_hidden_size_list': [32, 64, 64, 128], | |
| 'actor_head_hidden_size': 128, | |
| 'critic_head_hidden_size': 128, | |
| 'critic_head_layer_num': 2 | |
| }, | |
| 'learn': { | |
| 'learner': { | |
| 'train_iterations': 1000000000, | |
| 'dataloader': { | |
| 'num_workers': 0 | |
| }, | |
| 'log_policy': True, | |
| 'hook': { | |
| 'load_ckpt_before_run': '', | |
| 'log_show_after_iter': 100, | |
| 'save_ckpt_after_iter': 10000, | |
| 'save_ckpt_after_run': True | |
| }, | |
| 'cfg_type': 'BaseLearnerDict' | |
| }, | |
| 'update_per_collect': 18, | |
| 'batch_size': 128, | |
| 'learning_rate': 0.0001, | |
| 'value_weight': 1.0, | |
| 'entropy_weight': 0.005, | |
| 'clip_ratio': 0.1, | |
| 'adv_norm': False, | |
| 'ignore_done': False | |
| }, | |
| 'collect': { | |
| 'collector': {}, | |
| 'unroll_len': 1, | |
| 'discount_factor': 0.99, | |
| 'gae_lambda': 0.95, | |
| 'n_sample': 1024 | |
| }, | |
| 'eval': { | |
| 'evaluator': { | |
| 'eval_freq': 1000, | |
| 'render': { | |
| 'render_freq': -1, | |
| 'mode': 'train_iter' | |
| }, | |
| 'cfg_type': 'InteractionSerialEvaluatorDict', | |
| 'stop_value': 10000000000, | |
| 'n_episode': 8 | |
| } | |
| }, | |
| 'other': { | |
| 'replay_buffer': { | |
| 'replay_buffer_size': 10000 | |
| } | |
| }, | |
| 'on_policy': False, | |
| 'cuda': True, | |
| 'multi_gpu': False, | |
| 'bp_update_sync': True, | |
| 'traj_len_inf': False, | |
| 'type': 'ppo', | |
| 'priority': False, | |
| 'priority_IS_weight': False, | |
| 'nstep_return': False, | |
| 'nstep': 3, | |
| 'transition_with_policy_data': True, | |
| 'cfg_type': 'PPOOffPolicyDict' | |
| }, | |
| 'exp_name': 'QbertNoFrameskip-v4-PPOOffPolicy', | |
| 'wandb_logger': { | |
| 'gradient_logger': True, | |
| 'video_logger': True, | |
| 'plot_logger': True, | |
| 'action_logger': True, | |
| 'return_logger': False | |
| }, | |
| 'seed': 0 | |
| } | |