| from easydict import EasyDict | |
| lunarlander_ppo_config = dict( | |
| exp_name='lunarlander_ppo_seed0', | |
| env=dict( | |
| collector_env_num=8, | |
| evaluator_env_num=5, | |
| env_id='LunarLander-v2', | |
| n_evaluator_episode=5, | |
| stop_value=200, | |
| ), | |
| policy=dict( | |
| recompute_adv=True, | |
| cuda=True, | |
| action_space='discrete', | |
| model=dict( | |
| obs_shape=8, | |
| action_shape=4, | |
| action_space='discrete', | |
| ), | |
| learn=dict( | |
| epoch_per_collect=10, | |
| batch_size=64, | |
| learning_rate=3e-4, | |
| entropy_weight=0.01, | |
| adv_norm=True, | |
| value_norm=True, | |
| ), | |
| collect=dict( | |
| n_sample=512, | |
| discount_factor=0.99, | |
| ), | |
| ), | |
| ) | |
| lunarlander_ppo_config = EasyDict(lunarlander_ppo_config) | |
| main_config = lunarlander_ppo_config | |
| lunarlander_ppo_create_config = dict( | |
| env=dict( | |
| type='lunarlander', | |
| import_names=['dizoo.box2d.lunarlander.envs.lunarlander_env'], | |
| ), | |
| env_manager=dict(type='subprocess'), | |
| policy=dict(type='ppo'), | |
| ) | |
| lunarlander_ppo_create_config = EasyDict(lunarlander_ppo_create_config) | |
| create_config = lunarlander_ppo_create_config | |
| if __name__ == "__main__": | |
| from ding.entry import serial_pipeline_onpolicy | |
| serial_pipeline_onpolicy([main_config, create_config], seed=0) | |