!!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
    - true
  - - policy
    - MlpPolicy
  - - policy_kwargs
    - dict(activation_fn=nn.Tanh, net_arch=[dict(pi=[64, 64], vf=[64, 64])])
  - - vf_coef
    - 0.4351450387648799