!!python/object/apply:collections.OrderedDict
- - - batch_size
    - 16
  - - clip_range
    - 0.3
  - - ent_coef
    - 3.1441389214159857e-06
  - - gae_lambda
    - 0.8
  - - gamma
    - 0.995
  - - learning_rate
    - 0.00017959211641976886
  - - max_grad_norm
    - 0.9
  - - n_epochs
    - 10
  - - n_steps
    - 2048
  - - n_timesteps
    - 1000000.0
  - - normalize
    - gamma: 0.995
      norm_obs: false
      norm_reward: true
  - - policy
    - MlpPolicy
  - - policy_kwargs
    - activation_fn: !!python/name:torch.nn.modules.activation.Tanh ''
      features_extractor_class: !!python/name:imitation.policies.base.NormalizeFeaturesExtractor ''
      net_arch:
      - pi:
        - 64
        - 64
        vf:
        - 64
        - 64
  - - vf_coef
    - 0.4351450387648799