!!python/object/apply:collections.OrderedDict
- - - batch_size
    - 128
  - - buffer_size
    - 100000
  - - gamma
    - 0.98
  - - learning_rate
    - 0.001709807687567946
  - - learning_starts
    - 1000
  - - n_timesteps
    - 1000000.0
  - - policy
    - MlpPolicy
  - - policy_kwargs
    - log_std_init: -1.6829391077276037
      net_arch:
      - 256
      - 256
      use_sde: false
  - - tau
    - 0.08
  - - train_freq
    - 32