HenrySky

Results 1 comments of HenrySky

``` from easydict import EasyDict cartpole_dqn_config = dict( exp_name='cartpole_ppo', env=dict( collector_env_num=8, collector_episode_num=2, evaluator_env_num=5, evaluator_episode_num=1, stop_value=195, ), policy=dict( cuda=False, action_space='discrete', model=dict( obs_shape=4, action_shape=2, action_space='discrete', ), learn=dict( batch_size=32, learning_rate=0.001, value_weight=0.5, entropy_weight=0.01, clip_ratio=0.2,...