ding.config.example.TD3.gym_halfcheetah_v3

ding.config.example.TD3.gym_halfcheetah_v3

Full Source Code

../ding/config/example/TD3/gym_halfcheetah_v3.py

1from easydict import EasyDict 2import ding.envs.gym_env 3 4cfg = dict( 5 exp_name='HalfCheetah-v3-TD3', 6 seed=0, 7 env=dict( 8 env_id='HalfCheetah-v3', 9 collector_env_num=1, 10 evaluator_env_num=8, 11 n_evaluator_episode=8, 12 stop_value=11000, 13 env_wrapper='mujoco_default', 14 ), 15 policy=dict( 16 cuda=True, 17 random_collect_size=25000, 18 model=dict( 19 obs_shape=17, 20 action_shape=6, 21 twin_critic=True, 22 actor_head_hidden_size=256, 23 critic_head_hidden_size=256, 24 action_space='regression', 25 ), 26 learn=dict( 27 update_per_collect=1, 28 batch_size=256, 29 learning_rate_actor=1e-3, 30 learning_rate_critic=1e-3, 31 ignore_done=True, 32 target_theta=0.005, 33 discount_factor=0.99, 34 actor_update_freq=2, 35 noise=True, 36 noise_sigma=0.2, 37 noise_range=dict( 38 min=-0.5, 39 max=0.5, 40 ), 41 ), 42 collect=dict( 43 n_sample=1, 44 unroll_len=1, 45 noise_sigma=0.1, 46 ), 47 other=dict(replay_buffer=dict(replay_buffer_size=1000000, ), ), 48 ), 49 wandb_logger=dict( 50 gradient_logger=True, video_logger=True, plot_logger=True, action_logger=True, return_logger=False 51 ), 52) 53 54cfg = EasyDict(cfg) 55 56env = ding.envs.gym_env.env