Model-free or learning-based control, in particular, reinforcement learning (RL), is expected to be applied for complex robotic tasks. Traditional RL requires a policy to be optimized is state-dependent, that means, the policy is a kind of feedback (FB) controllers. Due to the necessity of correct state observation in such a FB controller, it is sensitive to sensing failures. To alleviate this drawback of the FB controllers, feedback error learning integrates one of them with a feedforward (FF) controller. RL can be improved by dealing with the FB/FF policies, but to the best of our knowledge, a methodology for learning them in a unified manner has not been developed. In this paper, we propose a new optimization problem for optimizing both the FB/FF policies simultaneously. Inspired by control as inference, the optimization problem considers minimization/maximization of divergences between trajectory, predicted by the composed policy and a stochastic dynamics model, and optimal/non-optimal trajectories. By approximating the stochastic dynamics model using variational method, we naturally derive a regularization between the FB/FF policies. In numerical simulations and a robot experiment, we verified that the proposed method can stably optimize the composed policy even with the different learning law from the traditional RL. In addition, we demonstrated that the FF policy is robust to the sensing failures and can hold the optimal motion. Attached video is also uploaded on youtube: https://youtu.be/zLL4uXIRmrE
翻译:常规 RL 要求优化政策, 以国家为主, 这意味着该政策是一种反馈控制器。 由于在 FB 控制器中进行正确状态观测的必要性, 它对于感测失败十分敏感 。 为了减轻FB 控制器的这一缺陷, 反馈错误学习将其中之一与种子前向控制器( FF) 整合在一起 。 通过处理 FB/ FF 政策可以改进 RL 。 但对于我们的知识而言, 一种以统一方式学习这些政策的方法尚未开发出来。 这就意味着, 该政策是一种新型的 FB/ FF 控制器的反馈控制器( FB/ FB) 控制器( FB 控制器) 。 由于在这种FB 控制器中进行正确的状态观察, 反馈错误学习将其中之一与种子前向前的动态控制器( FF 控制器) 。 在使用变异性方法对随机的动态动态模型进行匹配时, 我们自然地对FBRFL 政策进行优化的模拟, 我们通过模拟法化法 。