arXiv subjects

Taisuke Kobayashi

Publications and source records attributed to Taisuke Kobayashi.

42 records · Page 3Linked to original sources

arXiv2021

Optimization Algorithm for Feedback and Feedforward Policies towards Robot Control Robust to Sensing Failures

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

cs.LG↗

arXiv2021

Proximal Policy Optimization with Relative Pearson Divergence

The recent remarkable progress of deep reinforcement learning (DRL) stands on regularization of policy for stable and efficient learning. A popular method, named proximal policy optimization (PPO), has been introduced for this purpose. PPO clips density ratio of the latest and baseline policies with a threshold, while its minimization target is unclear. As another problem of PPO, the symmetric threshold is given numerically while the density ratio itself is in asymmetric domain, thereby causing unbalanced regularization of the policy. This paper therefore proposes a new variant of PPO by considering a regularization problem of relative Pearson (RPE) divergence, so-called PPO-RPE. This regularization yields the clear minimization target, which constrains the latest policy to the baseline one. Through its analysis, the intuitive threshold-based design consistent with the asymmetry of the threshold and the domain of density ratio can be derived. Through four benchmark tasks, PPO-RPE performed as well as or better than the conventional methods in terms of the task performance by the learned policy.

cs.LG↗

arXiv2021

Deep unfolding-based output feedback control design for linear systems with input saturation

In this paper, we propose a deep unfolding-based framework for the output feedback control of systems with input saturation. Although saturation commonly arises in several practical control systems, there is still a scarce of effective design methodologies that can directly deal with the severe non-linearity of the saturation operator. In this paper, we aim to design an anti-windup controller for enlarging the region of stability of the closed-loop system by learning from the numerical simulations of the closed-loop system. The data-driven framework we propose in this paper is based on a deep-learning technique called Neural Ordinary Differential Equations. Within our framework, we first obtain a candidate controller by using the deep-learning technique, which is then tested by the existing theoretical results already established in the literature, thereby avoiding the computational challenge in the conventional design methodologies as well as theoretically guaranteeing the performance of the system. Our numerical simulation shows that the proposed framework can significantly outperform a conventional design methodology based on linear matrix inequalities.

eess.SY↗

arXiv2020

t-Soft Update of Target Network for Deep Reinforcement Learning

This paper proposes a new robust update rule of target network for deep reinforcement learning (DRL), to replace the conventional update rule, given as an exponential moving average. The target network is for smoothly generating the reference signals for a main network in DRL, thereby reducing learning variance. The problem with its conventional update rule is the fact that all the parameters are smoothly copied with the same speed from the main network, even when some of them are trying to update toward the wrong directions. This behavior increases the risk of generating the wrong reference signals. Although slowing down the overall update speed is a naive way to mitigate wrong updates, it would decrease learning speed. To robustly update the parameters while keeping learning speed, a t-soft update method, which is inspired by student-t distribution, is derived with reference to the analogy between the exponential moving average and the normal distribution. Through the analysis of the derived t-soft update, we show that it takes over the properties of the student-t distribution. Specifically, with a heavy-tailed property of the student-t distribution, the t-soft update automatically excludes extreme updates that differ from past experiences. In addition, when the updates are similar to the past experiences, it can mitigate the learning delay by increasing the amount of updates. In PyBullet robotics simulations for DRL, an online actor-critic algorithm with the t-soft update outperformed the conventional methods in terms of the obtained return and/or its variance. From the training process by the t-soft update, we found that the t-soft update is globally consistent with the standard soft update, and the update rates are locally adjusted for acceleration or suppression.

cs.LG↗

arXiv2020

Towards Deep Robot Learning with Optimizer applicable to Non-stationary Problems

This paper proposes a new optimizer for deep learning, named d-AmsGrad. In the real-world data, noise and outliers cannot be excluded from dataset to be used for learning robot skills. This problem is especially striking for robots that learn by collecting data in real time, which cannot be sorted manually. Several noise-robust optimizers have therefore been developed to resolve this problem, and one of them, named AmsGrad, which is a variant of Adam optimizer, has a proof of its convergence. However, in practice, it does not improve learning performance in robotics scenarios. This reason is hypothesized that most of robot learning problems are non-stationary, but AmsGrad assumes the maximum second momentum during learning to be stationarily given. In order to adapt to the non-stationary problems, an improved version, which slowly decays the maximum second momentum, is proposed. The proposed optimizer has the same capability of reaching the global optimum as baselines, and its performance outperformed that of the baselines in robotics problems.

cs.LG↗

arXiv2020

TAdam: A Robust Stochastic Gradient Optimizer

Machine learning algorithms aim to find patterns from observations, which may include some noise, especially in robotics domain. To perform well even with such noise, we expect them to be able to detect outliers and discard them when needed. We therefore propose a new stochastic gradient optimization method, whose robustness is directly built in the algorithm, using the robust student-t distribution as its core idea. Adam, the popular optimization method, is modified with our method and the resultant optimizer, so-called TAdam, is shown to effectively outperform Adam in terms of robustness against noise on diverse task, ranging from regression and classification to reinforcement learning problems. The implementation of our algorithm can be found at https://github.com/Mahoumaru/TAdam.git

cs.LG↗