| !!python/object/apply:collections.OrderedDict | |
| - - - batch_size | |
| - 128 | |
| - - clip_range | |
| - 0.2 | |
| - - ent_coef | |
| - 0.0 | |
| - - env_wrapper | |
| - - utils.wrappers.FrameSkip: | |
| skip: 2 | |
| - gym.wrappers.resize_observation.ResizeObservation: | |
| shape: 64 | |
| - gym.wrappers.gray_scale_observation.GrayScaleObservation: | |
| keep_dim: true | |
| - - frame_stack | |
| - 2 | |
| - - gae_lambda | |
| - 0.95 | |
| - - gamma | |
| - 0.99 | |
| - - learning_rate | |
| - lin_1e-4 | |
| - - max_grad_norm | |
| - 0.5 | |
| - - n_envs | |
| - 8 | |
| - - n_epochs | |
| - 10 | |
| - - n_steps | |
| - 512 | |
| - - n_timesteps | |
| - 4000000.0 | |
| - - normalize | |
| - '{''norm_obs'': False, ''norm_reward'': True}' | |
| - - policy | |
| - CnnPolicy | |
| - - policy_kwargs | |
| - dict(log_std_init=-2, ortho_init=False, activation_fn=nn.GELU, net_arch=[dict(pi=[256], | |
| vf=[256])], ) | |
| - - sde_sample_freq | |
| - 4 | |
| - - use_sde | |
| - true | |
| - - vf_coef | |
| - 0.5 | |