!!python/object/apply:collections.OrderedDict
- - - batch_size
    - 512
  - - clip_range
    - 0.2
  - - ent_coef
    - 0.00066
  - - gae_lambda
    - 0.9978
  - - gamma
    - 0.99779
  - - learning_rate
    - 0.00044
  - - max_grad_norm
    - 0.77
  - - n_envs
    - 16
  - - n_epochs
    - 10
  - - n_steps
    - 2048
  - - n_timesteps
    - 1000000.0
  - - normalize
    - true
  - - policy
    - MultiInputPolicy
  - - policy_kwargs
    - dict( net_arch=[256, 256], activation_fn=nn.ReLU )