!!python/object/apply:collections.OrderedDict - - - batch_size - 256 - - clip_range - 0.1 - - ent_coef - 0.00429 - - gae_lambda - 0.9 - - gamma - 0.9999 - - learning_rate - 7.77e-05 - - max_grad_norm - 5 - - n_envs - 1 - - n_epochs - 10 - - n_steps - 8 - - n_timesteps - 20000.0 - - normalize - true - - policy - MlpPolicy - - policy_kwargs - dict(log_std_init=-3.29, ortho_init=False) - - use_sde - true - - vf_coef - 0.19