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 2006.02750cs.LGmath.OCstat.ML
收藏

不确定动态优化的约束强化学习

Constrained Reinforcement Learning for Dynamic Optimization under Uncertainty

University College London(伦敦大学学院);Universidad Nacional Autónoma de México(墨西哥国立自治大学);Norwegian University of Science and Technology(挪威科技大学);The University of Manchester(曼彻斯特大学);Imperial College London(帝国理工学院)

Panagiotis Petsagkourakis, Ilya Orson Sandoval, Eric Bradford, Dongda Zhang, Ehecatl Antonio del Río Chanona

摘要:

动态实时优化(DRTO)是一项具有挑战性的任务,因为必须实时的计算最佳操作条件。DRTO工业应用的主要瓶颈是不确定性的存在。许多随机系统存在以下障碍:1)工厂模型不匹配,2)过程干扰,3)违反过程约束的风险。为了适应这些困难,我们提出了一种基于约束强化学习(RL)的方法。RL通过计算最优反馈策略自然地处理过程不确定性。然而,不能直观地引入状态约束。为了解决这个问题,我们提出了一个机会约束强化学习方法。我们使用机会约束来保证过程约束的概率满足,这是通过引入退避来实现的,使得最优策略和退避同时计算。使用经验累积分布函数来调整回退,以保证满足联合机会约束。通过一个随机动态生物过程优化问题说明了该策略的优势和性能,以生产可持续的高价值生物产品。

英文摘要:

Dynamic real-time optimization (DRTO) is a challenging task due to the fact that optimal operating conditions must be computed in real time. The main bottleneck in the industrial application of DRTO is the presence of uncertainty. Many stochastic systems present the following obstacles: 1) plant-model mismatch, 2) process disturbances, 3) risks in violation of process constraints. To accommodate these difficulties, we present a constrained reinforcement learning (RL) based approach. RL naturally handles the process uncertainty by computing an optimal feedback policy. However, no state constraints can be introduced intuitively. To address this problem, we present a chance-constrained RL methodology. We use chance constraints to guarantee the probabilistic satisfaction of process constraints, which is accomplished by introducing backoffs, such that the optimal policy and backoffs are computed simultaneously. Backoffs are adjusted using the empirical cumulative distribution function to guarantee the satisfaction of a joint chance constraint. The advantage and performance of this strategy are illustrated through a stochastic dynamic bioprocess optimization problem, to produce sustainable high-value bioproducts.

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。

↑