Randomized Optimal Stopping Problem in Continuous time and Reinforcement Learning Algorithm
From MaRDI portal
Abstract: In this paper, we study the optimal stopping problem in the so-called exploratory framework, in which the agent takes actions randomly conditioning on current state and an entropy-regularized term is added to the reward functional. Such a transformation reduces the optimal stopping problem to a standard optimal control problem. We derive the related HJB equation and prove its solvability. Furthermore, we give a convergence rate of policy iteration and the comparison to classical optimal stopping problem. Based on the theoretical analysis, a reinforcement learning algorithm is designed and numerical results are demonstrated for several models.
Recommendations
- Randomized Optimal Stopping Algorithms and Their Convergence Analysis
- A new learning algorithm for optimal stopping
- Optimal stopping via reinforced regression
- Solving Optimal Stopping Problems via Randomization and Empirical Dual Optimization
- Deep combinatorial optimisation for optimal stopping time problems: application to swing options pricing.
Cited in
(6)- Control randomisation approach for policy gradient and application to reinforcement learning in optimal switching
- Time-inconsistent mean-field stopping problems: a regularised equilibrium approach
- Guaranteed bounds for optimal stopping problems using kernel-based non-asymptotic uniform confidence bands
- Entropy annealing for policy mirror descent in continuous time and space
- Policy iteration for exploratory Hamilton-Jacobi-Bellman equations
- Convergence analysis for entropy-regularized control problems: a probabilistic approach
This page was built for publication: Randomized Optimal Stopping Problem in Continuous time and Reinforcement Learning Algorithm
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6406925)
