| !!python/object/apply:collections.OrderedDict | |
| - - - batch_size | |
| - 256 | |
| - - buffer_size | |
| - 300000 | |
| - - ent_coef | |
| - auto | |
| - - env_wrapper | |
| - sb3_contrib.common.wrappers.TimeFeatureWrapper | |
| - - gamma | |
| - 0.98 | |
| - - gradient_steps | |
| - 64 | |
| - - learning_rate | |
| - lin_7.3e-4 | |
| - - learning_starts | |
| - 10000 | |
| - - n_timesteps | |
| - 1000000.0 | |
| - - policy | |
| - MlpPolicy | |
| - - policy_kwargs | |
| - dict(log_std_init=-3, net_arch=[400, 300]) | |
| - - tau | |
| - 0.02 | |
| - - train_freq | |
| - 64 | |
| - - use_sde | |
| - true | |