!!python/object/apply:collections.OrderedDict
- - - batch_size
    - 256
  - - gae_lambda
    - 0.98
  - - gamma
    - 0.9999
  - - learning_rate
    - 0.0006
  - - n_envs
    - 4
  - - n_steps
    - 1024
  - - n_timesteps
    - 1000000.0
  - - normalize
    - true
  - - policy
    - MlpPolicy