{'_logits._model.0.weight': (20, 256), '_logits._model.0.bias': (20,), '_hidden_layers.0._model.0.weight': (256, 10), '_hidden_layers.0._model.0.bias': (256,), '_hidden_layers.1._model.0.weight': (256, 256), '_hidden_layers.1._model.0.bias': (256,), '_value_branch_separate.0._model.0.weight': (256, 10), '_value_branch_separate.0._model.0.bias': (256,), '_value_branch_separate.1._model.0.weight': (256, 256), '_value_branch_separate.1._model.0.bias': (256,), '_value_branch._model.0.weight': (1, 256), '_value_branch._model.0.bias': (1,)}