zjowowen's picture
Upload policy_config.py with huggingface_hub
75f8ef4
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': 2000,
'n_evaluator_episode': 8,
'env_id': 'SpaceInvadersNoFrameskip-v4',
'collector_env_num': 8,
'evaluator_env_num': 8,
'fram_stack': 4,
'env_wrapper': 'atari_default'
},
'policy': {
'model': {
'obs_shape': [4, 84, 84],
'action_shape': 6,
'encoder_hidden_size_list': [128, 128, 256, 256],
'critic_head_hidden_size': 256,
'critic_head_layer_num': 3,
'actor_head_hidden_size': 256,
'actor_head_layer_num': 3
},
'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': 2,
'batch_size': 128,
'learning_rate': 0.0006,
'value_weight': 0.5,
'entropy_weight': 0.01,
'discount_factor': 0.99,
'lambda_': 0.95,
'rho_clip_ratio': 1.0,
'c_clip_ratio': 1.0,
'rho_pg_clip_ratio': 1.0,
'grad_clip_type': 'clip_norm',
'clip_value': 5
},
'collect': {
'collector': {
'collect_print_freq': 1000
},
'n_sample': 16,
'unroll_len': 64
},
'eval': {
'evaluator': {
'eval_freq': 500,
'render': {
'render_freq': -1,
'mode': 'train_iter'
},
'figure_path': None,
'cfg_type': 'InteractionSerialEvaluatorDict',
'stop_value': 2000,
'n_episode': 8
}
},
'other': {
'replay_buffer': {
'replay_buffer_size': 64000,
'max_use': 16,
'sliced': True
}
},
'on_policy': False,
'cuda': True,
'multi_gpu': False,
'bp_update_sync': True,
'traj_len_inf': False,
'type': 'impala',
'priority': False,
'priority_IS_weight': False,
'action_space': 'discrete',
'unroll_len': 64,
'transition_with_policy_data': True,
'cfg_type': 'IMPALAPolicyDict',
'random_collect_size': 5000
},
'exp_name': 'SpaceInvadersNoFrameskip-v4-IMPALA',
'seed': 0,
'wandb_logger': {
'gradient_logger': True,
'video_logger': True,
'plot_logger': True,
'action_logger': True,
'return_logger': False
}
}