| !!python/object/apply:collections.OrderedDict | |
| - - - batch_size | |
| - 64 | |
| - - buffer_size | |
| - 100000 | |
| - - exploration_final_eps | |
| - 0.04 | |
| - - exploration_fraction | |
| - 0.16 | |
| - - gamma | |
| - 0.99 | |
| - - gradient_steps | |
| - 128 | |
| - - learning_rate | |
| - 0.0023 | |
| - - learning_starts | |
| - 1000 | |
| - - n_timesteps | |
| - 50000.0 | |
| - - policy | |
| - MlpPolicy | |
| - - policy_kwargs | |
| - dict(net_arch=[256, 256]) | |
| - - target_update_interval | |
| - 10 | |
| - - train_freq | |
| - 256 | |