!!python/object/apply:collections.OrderedDict
- - - batch_size
    - 9
  - - buffer_size
    - 56569
  - - exploration_final_eps
    - 0.1
  - - exploration_fraction
    - 0.1164397832458963
  - - exploration_initial_eps
    - 0.03696153798457299
  - - gamma
    - 0.0006190974200887802
  - - gradient_steps
    - 9
  - - learning_rate
    - 0.011288061590135373
  - - learning_starts
    - 15731
  - - max_grad_norm
    - 3.705892661777349
  - - n_timesteps
    - 10000000.0
  - - policy
    - MlpPolicy
  - - policy_kwargs
    - dict(net_arch=[256, 256])
  - - target_update_interval
    - 218430
  - - tau
    - 0.04363931503941886
  - - train_freq
    - !!python/tuple
      - 9
      - episode