| !!python/object/apply:collections.OrderedDict | |
| - - - batch_size | |
| - 512 | |
| - - clip_range | |
| - 0.2 | |
| - - ent_coef | |
| - 6.4940755116195606e-06 | |
| - - gae_lambda | |
| - 0.98 | |
| - - gamma | |
| - 0.99 | |
| - - learning_rate | |
| - 0.0004476103728105138 | |
| - - max_grad_norm | |
| - 1 | |
| - - n_envs | |
| - 16 | |
| - - n_epochs | |
| - 20 | |
| - - n_steps | |
| - 256 | |
| - - n_timesteps | |
| - 1000000.0 | |
| - - normalize | |
| - dict(norm_obs=False, norm_reward=True) | |
| - - policy | |
| - imitation.policies.base.MlpPolicyWithNormalizeFeaturesExtractor | |
| - - policy_kwargs | |
| - dict(activation_fn=nn.Tanh, net_arch=[dict(pi=[64, 64], vf=[64, 64])]) | |
| - - vf_coef | |
| - 0.25988158989488963 | |