!!python/object/apply:collections.OrderedDict
- - - batch_size
    - 128
  - - buffer_size
    - 10000
  - - exploration_final_eps
    - 0.07
  - - exploration_fraction
    - 0.2
  - - gamma
    - 0.98
  - - gradient_steps
    - 8
  - - learning_rate
    - 0.004
  - - learning_starts
    - 1000
  - - n_timesteps
    - 120000.0
  - - policy
    - MlpPolicy
  - - policy_kwargs
    - dict(net_arch=[256, 256])
  - - target_update_interval
    - 600
  - - train_freq
    - 16