!!python/object/apply:collections.OrderedDict
- - - batch_size
    - 32
  - - clip_range
    - 0.2
  - - ent_coef
    - 0.00229519
  - - gae_lambda
    - 0.99
  - - gamma
    - 0.999
  - - learning_rate
    - 9.80828e-05
  - - max_grad_norm
    - 0.7
  - - n_envs
    - 1
  - - n_epochs
    - 5
  - - n_steps
    - 512
  - - n_timesteps
    - 1000000.0
  - - normalize
    - true
  - - policy
    - MlpPolicy
  - - policy_kwargs
    - dict( log_std_init=-2, ortho_init=False, activation_fn=nn.ReLU, net_arch=[dict(pi=[256,
      256], vf=[256, 256])] )
  - - vf_coef
    - 0.835671