arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.01738cs.LGstat.ML
收藏

投影随机梯度上升联合学习环境与控制策略

Jointly Learning Environments and Control Policies with Projected Stochastic Gradient Ascent

Montefiore Institute(蒙特菲奥里研究所);University of Liège(列日大学)

Adrien Bolland, Ioannis Boukas, Mathias Berger, Damien Ernst

摘要:

我们考虑有限时间范围内离散随机动力系统的联合设计和控制。我们制定的问题作为一个多步骤的不确定性下的优化问题,寻求确定一个系统的设计和控制策略,共同最大限度地提高预期的回报总额在考虑的时间范围内收集。转移函数、奖励函数和策略都是参数化的,假设它们的参数是已知的和可微的。然后,我们引入了一个深度强化学习算法结合策略梯度方法与基于模型的优化技术来解决这个问题。从本质上讲,我们的算法迭代近似的梯度的预期收益率通过蒙特卡洛采样和自动微分,并采取投影梯度上升步骤中的环境和政策参数的空间。该算法被称为直接环境和策略搜索(DEPS)。我们评估我们的算法在三个环境中的性能有关的质量弹簧阻尼器系统的设计和控制,一个小规模的离网电力系统和无人机,分别。此外,我们的算法是对一个国家的最先进的深度强化学习算法用于解决关节设计和控制问题的基准。我们表明,DEPS在所有三种环境中至少表现得一样好或更好,在更少的迭代中始终产生具有更高回报的解决方案。最后,我们的算法产生的解决方案也比较了一个算法,不联合优化环境和政策参数,突出的事实是,更高的回报,可以实现联合优化时产生的解决方案。

英文摘要:

We consider the joint design and control of discrete-time stochastic dynamical systems over a finite time horizon. We formulate the problem as a multi-step optimization problem under uncertainty seeking to identify a system design and a control policy that jointly maximize the expected sum of rewards collected over the time horizon considered. The transition function, the reward function and the policy are all parametrized, assumed known and differentiable with respect to their parameters. We then introduce a deep reinforcement learning algorithm combining policy gradient methods with model-based optimization techniques to solve this problem. In essence, our algorithm iteratively approximates the gradient of the expected return via Monte-Carlo sampling and automatic differentiation and takes projected gradient ascent steps in the space of environment and policy parameters. This algorithm is referred to as Direct Environment and Policy Search (DEPS). We assess the performance of our algorithm in three environments concerned with the design and control of a mass-spring-damper system, a small-scale off-grid power system and a drone, respectively. In addition, our algorithm is benchmarked against a state-of-the-art deep reinforcement learning algorithm used to tackle joint design and control problems. We show that DEPS performs at least as well or better in all three environments, consistently yielding solutions with higher returns in fewer iterations. Finally, solutions produced by our algorithm are also compared with solutions produced by an algorithm that does not jointly optimize environment and policy parameters, highlighting the fact that higher returns can be achieved when joint optimization is performed.

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。

↑