| !!python/object/apply:collections.OrderedDict | |
| - - - ent_coef | |
| - 0.0 | |
| - - env_wrapper | |
| - sb3_contrib.common.wrappers.TimeFeatureWrapper | |
| - - gae_lambda | |
| - 0.9 | |
| - - gamma | |
| - 0.99 | |
| - - learning_rate | |
| - lin_0.00096 | |
| - - max_grad_norm | |
| - 0.5 | |
| - - n_envs | |
| - 4 | |
| - - n_steps | |
| - 8 | |
| - - n_timesteps | |
| - 2000000.0 | |
| - - normalize | |
| - true | |
| - - normalize_advantage | |
| - false | |
| - - policy | |
| - MlpPolicy | |
| - - policy_kwargs | |
| - dict(log_std_init=-2, ortho_init=False, full_std=True) | |
| - - use_rms_prop | |
| - true | |
| - - use_sde | |
| - true | |
| - - vf_coef | |
| - 0.4 | |