!!python/object/apply:collections.OrderedDict
- - - batch_size
    - 128
  - - buffer_size
    - 100000
  - - gamma
    - 0.99
  - - learning_rate
    - 0.0005845844772048097
  - - learning_starts
    - 1000
  - - n_timesteps
    - 1000000.0
  - - policy
    - MlpPolicy
  - - policy_kwargs
    - dict(net_arch=[400, 300], log_std_init=0.1955317469998743)
  - - tau
    - 0.02
  - - train_freq
    - 1