| !!python/object/apply:collections.OrderedDict | |
| - - - batch_size | |
| - 128 | |
| - - clip_range | |
| - lin_0.4 | |
| - - ent_coef | |
| - 0.0 | |
| - - env_wrapper | |
| - sb3_contrib.common.wrappers.TimeFeatureWrapper | |
| - - gae_lambda | |
| - 0.92 | |
| - - gamma | |
| - 0.99 | |
| - - learning_rate | |
| - 3.0e-05 | |
| - - max_grad_norm | |
| - 0.5 | |
| - - n_envs | |
| - 16 | |
| - - n_epochs | |
| - 20 | |
| - - n_steps | |
| - 512 | |
| - - n_timesteps | |
| - 2000000.0 | |
| - - normalize | |
| - true | |
| - - policy | |
| - MlpPolicy | |
| - - policy_kwargs | |
| - dict(log_std_init=-2, ortho_init=False, activation_fn=nn.ReLU, net_arch=[dict(pi=[256, | |
| 256], vf=[256, 256])] ) | |
| - - sde_sample_freq | |
| - 4 | |
| - - use_sde | |
| - true | |
| - - vf_coef | |
| - 0.5 | |