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 2201.00039cs.LGmath.OC
收藏

可证明有效学徒学习的随机凸优化

Stochastic convex optimization for provably efficient apprenticeship learning

ETH Zurich(苏黎世联邦理工学院)

Angeliki Kamoutsi, Goran Banjac, John Lygeros

摘要:

我们考虑大规模马尔可夫决策过程(MDP)与未知的成本函数,并采用随机凸优化工具来解决问题的模仿学习,其中包括学习的政策,从一个有限的专家演示。我们采用学徒学习的形式主义,它进行的假设,真正的成本函数可以表示为一些已知的功能的线性组合。现有的逆强化学习算法具有很强的理论保证,但由于它们使用强化学习或规划算法作为子例程,因此计算成本很高。另一方面,最先进的基于策略梯度的算法(如IM-REINFORCE、IM-TRPO和GAIL)在挑战性基准任务中取得了显著的经验成功,但在理论方面还没有得到很好的理解。强调非渐近保证性能,我们提出了一种方法,直接学习的政策,从专家演示,绕过学习成本函数的中间步骤,制定的问题作为一个单一的凸优化问题的占用措施。我们开发了一个计算效率高的算法,并获得高置信度的遗憾界提取的政策的质量,利用随机凸优化和最近的工作,在近似线性规划求解正向MDPs的结果。

英文摘要:

We consider large-scale Markov decision processes (MDPs) with an unknown cost function and employ stochastic convex optimization tools to address the problem of imitation learning, which consists of learning a policy from a finite set of expert demonstrations. We adopt the apprenticeship learning formalism, which carries the assumption that the true cost function can be represented as a linear combination of some known features. Existing inverse reinforcement learning algorithms come with strong theoretical guarantees, but are computationally expensive because they use reinforcement learning or planning algorithms as a subroutine. On the other hand, state-of-the-art policy gradient based algorithms (like IM-REINFORCE, IM-TRPO, and GAIL), achieve significant empirical success in challenging benchmark tasks, but are not well understood in terms of theory. With an emphasis on non-asymptotic guarantees of performance, we propose a method that directly learns a policy from expert demonstrations, bypassing the intermediate step of learning the cost function, by formulating the problem as a single convex optimization problem over occupancy measures. We develop a computationally efficient algorithm and derive high confidence regret bounds on the quality of the extracted policy, utilizing results from stochastic convex optimization and recent works in approximate linear programming for solving forward MDPs.

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。

↑