!!python/object/apply:collections.OrderedDict - - - batch_size - 64 - - buffer_size - 100000 - - gamma - 0.98 - - learning_rate - 4.426351861707874e-05 - - learning_starts - 20000 - - n_timesteps - 2000000.0 - - policy - MlpPolicy - - policy_kwargs - dict(net_arch=[400, 300], log_std_init=-0.1034412732183072) - - tau - 0.08 - - train_freq - 8