Skip to content

ding.config.example.SQL.gym_lunarlander_v2

ding.config.example.SQL.gym_lunarlander_v2

Full Source Code

../ding/config/example/SQL/gym_lunarlander_v2.py

1from easydict import EasyDict 2import ding.envs.gym_env 3 4cfg = dict( 5 exp_name='LunarLander-v2-SQL', 6 env=dict( 7 collector_env_num=8, 8 evaluator_env_num=8, 9 env_id='LunarLander-v2', 10 n_evaluator_episode=8, 11 stop_value=260, 12 ), 13 policy=dict( 14 cuda=True, 15 model=dict( 16 obs_shape=8, 17 action_shape=4, 18 encoder_hidden_size_list=[128, 128, 64], 19 dueling=True, 20 ), 21 nstep=1, 22 discount_factor=0.97, 23 learn=dict(batch_size=64, learning_rate=0.001, alpha=0.08), 24 collect=dict(n_sample=64), 25 eval=dict(evaluator=dict(eval_freq=50, )), # note: this is the times after which you learns to evaluate 26 other=dict( 27 eps=dict( 28 type='exp', 29 start=0.95, 30 end=0.1, 31 decay=10000, 32 ), 33 replay_buffer=dict(replay_buffer_size=20000, ), 34 ), 35 ), 36 wandb_logger=dict( 37 gradient_logger=True, video_logger=True, plot_logger=True, action_logger=True, return_logger=False 38 ), 39) 40 41cfg = EasyDict(cfg) 42 43env = ding.envs.gym_env.env