Spaces:
Sleeping
Sleeping
| from easydict import EasyDict | |
| cartpole_impala_config = dict( | |
| exp_name='cartpole_impala_seed0', | |
| env=dict( | |
| collector_env_num=8, | |
| evaluator_env_num=5, | |
| n_evaluator_episode=5, | |
| stop_value=195, | |
| ), | |
| policy=dict( | |
| cuda=False, | |
| model=dict( | |
| obs_shape=4, | |
| action_shape=2, | |
| encoder_hidden_size_list=[64, 64], | |
| ), | |
| # (int) the trajectory length to calculate v-trace target | |
| unroll_len=8, | |
| learn=dict( | |
| # (int) collect n_sample data, train model update_per_collect times | |
| # here we follow ppo serial pipeline | |
| update_per_collect=4, | |
| # (int) the number of data for a train iteration | |
| batch_size=16, | |
| learning_rate=0.0005, | |
| # (float) loss weight of the value network, the weight of policy network is set to 1 | |
| value_weight=0.5, | |
| # (float) loss weight of the entropy regularization, the weight of policy network is set to 1 | |
| entropy_weight=0.0001, | |
| # (float) discount factor for future reward, defaults int [0, 1] | |
| discount_factor=0.9, | |
| # (float) additional discounting parameter | |
| lambda_=0.95, | |
| # (float) clip ratio of importance weights | |
| rho_clip_ratio=1.0, | |
| # (float) clip ratio of importance weights | |
| c_clip_ratio=1.0, | |
| # (float) clip ratio of importance sampling | |
| rho_pg_clip_ratio=1.0, | |
| ), | |
| collect=dict( | |
| # (int) collect n_sample data, train model n_iteration times | |
| n_sample=16, | |
| # (float) discount factor for future reward, defaults int [0, 1] | |
| discount_factor=0.9, | |
| gae_lambda=0.95, | |
| collector=dict(collect_print_freq=1000, ), | |
| ), | |
| eval=dict(evaluator=dict(eval_freq=200, )), | |
| other=dict(replay_buffer=dict( | |
| replay_buffer_size=1000, | |
| max_use=16, | |
| ), ), | |
| ), | |
| ) | |
| cartpole_impala_config = EasyDict(cartpole_impala_config) | |
| main_config = cartpole_impala_config | |
| cartpole_impala_create_config = dict( | |
| env=dict( | |
| type='cartpole', | |
| import_names=['dizoo.classic_control.cartpole.envs.cartpole_env'], | |
| ), | |
| env_manager=dict(type='base'), | |
| policy=dict(type='impala'), | |
| ) | |
| cartpole_impala_create_config = EasyDict(cartpole_impala_create_config) | |
| create_config = cartpole_impala_create_config | |
| if __name__ == "__main__": | |
| # or you can enter `ding -m serial -c cartpole_impala_config.py -s 0` | |
| from ding.entry import serial_pipeline | |
| serial_pipeline((main_config, create_config), seed=0) | |