!!python/object/apply:collections.OrderedDict
- - - batch_size
    - 256
  - - clip_range
    - 0.18
  - - ent_coef
    - 0.0
  - - gae_lambda
    - 0.95
  - - gamma
    - 0.999
  - - learning_rate
    - 0.0003
  - - n_envs
    - 32
  - - n_epochs
    - 10
  - - n_steps
    - 256
  - - n_timesteps
    - 5000000.0
  - - normalize
    - true
  - - policy
    - MlpLstmPolicy
  - - policy_kwargs
    - dict( ortho_init=False, activation_fn=nn.ReLU, lstm_hidden_size=64, enable_critic_lstm=True,
      net_arch=[dict(pi=[64], vf=[64])] )