39a0c98b1ec9adb55386544c870f99cb8ff8f447,slm_lab/env/__init__.py,OpenAIEnv,step,#OpenAIEnv#Any#,126

Before Change

        (state, reward, done, _info) = self.u_env.step(action)
        if not self.train_mode:
            self.u_env.render()
        reward_e = self.data_spaces["reward"].init_data_s(e=self.e)
        state_e = self.data_spaces["state"].init_data_s(e=self.e)
        done_e = self.data_spaces["done"].init_data_s(e=self.e)
        for (a, b), body in util.ndenumerate_nonan(self.body_e):
            reward_e[(a, b)] = reward

After Change

        (state, reward, done, _info) = self.u_env.step(action)
        if not self.train_mode:
            self.u_env.render()
        reward_e, state_e, done_e = self.env_space.aeb_space.init_data_s(
            ENV_DATA_NAMES, e=self.e)
        for (a, b), body in util.ndenumerate_nonan(self.body_e):
            reward_e[(a, b)] = reward

Instances