| !!python/object/apply:collections.OrderedDict | |
| - - - batch_size | |
| - 256 | |
| - - clip_range | |
| - lin_0.1 | |
| - - ent_coef | |
| - 0.01 | |
| - - env_wrapper | |
| - - stable_baselines3.common.atari_wrappers.AtariWrapper | |
| - - frame_stack | |
| - 4 | |
| - - gae_lambda | |
| - 0.9342974216877361 | |
| - - gamma | |
| - 0.999 | |
| - - learning_rate | |
| - lin_2.5e-4 | |
| - - n_envs | |
| - 8 | |
| - - n_epochs | |
| - 4 | |
| - - n_steps | |
| - 128 | |
| - - n_timesteps | |
| - 5000000.0 | |
| - - normalize | |
| - false | |
| - - policy | |
| - CnnPolicy | |
| - - policy_kwargs | |
| - dict(net_arch=[dict(pi=[64, 64], vf=[64, 64]),],activation_fn=nn.Tanh) | |
| - - vf_coef | |
| - 0.6 | |