| !!python/object/apply:collections.OrderedDict | |
| - - - batch_size | |
| - 512 | |
| - - buffer_size | |
| - 50000 | |
| - - ent_coef | |
| - 0.1 | |
| - - gamma | |
| - 0.9999 | |
| - - gradient_steps | |
| - 32 | |
| - - learning_rate | |
| - 0.0003 | |
| - - learning_starts | |
| - 0 | |
| - - n_timesteps | |
| - 50000.0 | |
| - - policy | |
| - MlpPolicy | |
| - - policy_kwargs | |
| - dict(log_std_init=-3.67, net_arch=[64, 64]) | |
| - - tau | |
| - 0.01 | |
| - - train_freq | |
| - 32 | |
| - - use_sde | |
| - true | |