| !!python/object/apply:collections.OrderedDict | |
| - - - batch_size | |
| - 8 | |
| - - clip_range | |
| - 0.1 | |
| - - ent_coef | |
| - 5.167107294612664e-08 | |
| - - gae_lambda | |
| - 0.95 | |
| - - gamma | |
| - 0.999 | |
| - - learning_rate | |
| - 0.0001214437022727675 | |
| - - max_grad_norm | |
| - 2 | |
| - - n_epochs | |
| - 20 | |
| - - n_steps | |
| - 2048 | |
| - - n_timesteps | |
| - 1000000.0 | |
| - - normalize | |
| - true | |
| - - policy | |
| - MlpPolicy | |
| - - policy_kwargs | |
| - dict(activation_fn=nn.Tanh, net_arch=[dict(pi=[64, 64], vf=[64, 64])]) | |
| - - vf_coef | |
| - 0.6162112311062333 | |