525f94ff0bfdb617175791a36f37bdd4ccb808d0,ml/rl/test/preprocessing/test_feature_extractor.py,TestTrainingFeatureExtractor,test_extract_max_q_discrete_action,#TestTrainingFeatureExtractor#,196

Before Change

        )
        // Setup
        ws, net = self.create_ws_and_net(extractor)
        input_record = net.input_record() + schema.NewRecord(
            net, schema.Struct(("reward", schema.Scalar()))
        )
        self.setup_state_features(ws, input_record.state_features)
        self.setup_next_state_features(ws, input_record.next_state_features)
        action = self.setup_action(ws, input_record.action)
        possible_next_actions = self.setup_possible_next_actions(

After Change

        res = extractor.extract(ws, input_record, net.output_record())
        o = res.training_input
        npt.assert_array_equal(reward.reshape(-1, 1), o.reward.numpy())
        npt.assert_array_equal(
            extra_data.episode_value.reshape(-1, 1), res.extras.episode_value.numpy()
        )
        npt.assert_array_equal(
            extra_data.action_probability.reshape(-1, 1),
            res.extras.action_probability.numpy(),
        )

Instances