arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2009.13097math.OCcs.SYeess.SY
收藏

最大熵最优控制的Hamilton Jacobi Bellman方程

Hamilton-Jacobi-Bellman Equations for Maximum Entropy Optimal Control

Jeongho Kim, Insoon Yang

摘要:

最大熵强化学习(RL)方法已成功应用于一系列具有挑战性的顺序决策和控制任务。然而,大多数现有的技术是针对离散时间系统设计的。作为扩展到连续时间系统的第一步,本文考虑了具有熵正则化的连续时间确定性最优控制问题。应用动态规划原理,导出了一类新的Hamilton-Jacobi-Bellman(HJB)方程,证明了最大熵控制问题的最优值函数对应于HJB方程的唯一黏性解.我们的最大熵配方示出,以提高黏性解的规律性,并渐近一致的熵正则化的效果减小。HJB方程的一个显著特点是计算易处理性。推广的Hopf-Lax公式可用于求解HJB方程,无需数值优化哈密顿量,且易于无网格求解。我们进一步证明了在控制仿射系统的情况下,最优控制是唯一的高斯型的,并且对于线性二次型问题,HJB方程被简化为Riccati方程,从而可以得到最优控制的显式表达式.最后,我们讨论了如何通过自适应动态规划方法将我们的结果扩展到无连续时间模型的强化学习。据我们所知,由此产生的算法是第一个数据驱动的控制方法,在连续时间内使用信息理论探索机制。

英文摘要:

Maximum entropy reinforcement learning (RL) methods have been successfully applied to a range of challenging sequential decision-making and control tasks. However, most of existing techniques are designed for discrete-time systems. As a first step toward their extension to continuous-time systems, this paper considers continuous-time deterministic optimal control problems with entropy regularization. Applying the dynamic programming principle, we derive a novel class of Hamilton-Jacobi-Bellman (HJB) equations and prove that the optimal value function of the maximum entropy control problem corresponds to the unique viscosity solution of the HJB equation. Our maximum entropy formulation is shown to enhance the regularity of the viscosity solution and to be asymptotically consistent as the effect of entropy regularization diminishes. A salient feature of the HJB equations is computational tractability. Generalized Hopf-Lax formulas can be used to solve the HJB equations in a tractable grid-free manner without the need for numerically optimizing the Hamiltonian. We further show that the optimal control is uniquely characterized as Gaussian in the case of control affine systems and that, for linear-quadratic problems, the HJB equation is reduced to a Riccati equation, which can be used to obtain an explicit expression of the optimal control. Lastly, we discuss how to extend our results to continuous-time model-free RL by taking an adaptive dynamic programming approach. To our knowledge, the resulting algorithms are the first data-driven control methods that use an information theoretic exploration mechanism in continuous time.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑