arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1904.09366cs.AI
收藏

基于学习神经网络转移模型的计划报酬潜力

Reward Potentials for Planning with Learned Neural Network Transition Models

University of Toronto(多伦多大学);Vector Institute(矢量研究所);Australian National University(澳大利亚国立大学)

Buser Say, Scott Sanner, Sylvie Thiébaux

摘要:

基于混合整数线性规划(MILP)的神经网络(NN)模型在连续动作和状态空间中的最优规划对于分支定界求解器来说是一项具有挑战性的任务,因为MILP模型的线性松弛性很差。对于一组给定的功能,潜在的竞争力提供了一个有效的框架计算成本(奖励)函数的界限。在本文中,我们模型的学习NN模型作为一个双层规划,并解决它使用一种新的有限时间约束生成算法找到最佳的潜在界限的问题。然后,我们通过引入约束条件来约束基于预先计算的奖励潜力的奖励函数,从而加强了底层MILP模型的线性松弛。在实验中,我们表明,我们的算法有效地计算奖励潜力学习NN模型,计算奖励潜力的开销是合理的总体加强的基础MILP模型的长期规划任务。

英文摘要:

Optimal planning with respect to learned neural network (NN) models in continuous action and state spaces using mixed-integer linear programming (MILP) is a challenging task for branch-and-bound solvers due to the poor linear relaxation of the underlying MILP model. For a given set of features, potential heuristics provide an efficient framework for computing bounds on cost (reward) functions. In this paper, we model the problem of finding optimal potential bounds for learned NN models as a bilevel program, and solve it using a novel finite-time constraint generation algorithm. We then strengthen the linear relaxation of the underlying MILP model by introducing constraints to bound the reward function based on the precomputed reward potentials. Experimentally, we show that our algorithm efficiently computes reward potentials for learned NN models, and that the overhead of computing reward potentials is justified by the overall strengthening of the underlying MILP model for the task of planning over long horizons.

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。

↑