PPO-LunarLander-v2 / config.yml
alperenunlu's picture
Tune Hyperparameters.
7be737d
!!python/object/apply:collections.OrderedDict
- - - batch_size
- 8
- - clip_range
- 0.2
- - ent_coef
- 0.0012069732975503813
- - gae_lambda
- 0.95
- - gamma
- 0.999
- - learning_rate
- 0.0004080379698108855
- - max_grad_norm
- 0.5
- - n_envs
- 16
- - n_epochs
- 10
- - n_steps
- 256
- - n_timesteps
- 2000000.0
- - policy
- MlpPolicy
- - vf_coef
- 0.3326356386659747