| !!python/object/apply:collections.OrderedDict | |
| - - - batch_size | |
| - 128 | |
| - - buffer_size | |
| - 50000 | |
| - - exploration_final_eps | |
| - 0.1 | |
| - - exploration_fraction | |
| - 0.12 | |
| - - gamma | |
| - 0.99 | |
| - - gradient_steps | |
| - -1 | |
| - - learning_rate | |
| - 0.00063 | |
| - - learning_starts | |
| - 0 | |
| - - n_timesteps | |
| - 100000.0 | |
| - - policy | |
| - MlpPolicy | |
| - - policy_kwargs | |
| - dict(net_arch=[256, 256], n_quantiles=25) | |
| - - target_update_interval | |
| - 250 | |
| - - train_freq | |
| - 4 | |