| !!python/object/apply:collections.OrderedDict | |
| - - - batch_size | |
| - 500 | |
| - - buffer_size | |
| - 500000 | |
| - - ent_coef | |
| - auto | |
| - - gamma | |
| - 0.99 | |
| - - gradient_steps | |
| - -1 | |
| - - learning_rate | |
| - 0.0003 | |
| - - learning_starts | |
| - 10000 | |
| - - n_timesteps | |
| - 1000000.0 | |
| - - policy | |
| - MlpPolicy | |
| - - policy_kwargs | |
| - dict(log_std_init=-3, net_arch=[256, 256]) | |
| - - tau | |
| - 0.005 | |
| - - train_freq | |
| - - 1 | |
| - episode | |