ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 1805.04238
12
17

Stochastic Approximation for Risk-aware Markov Decision Processes

11 May 2018
Wenjie Huang
W. Haskell
ArXivPDFHTML
Abstract

We develop a stochastic approximation-type algorithm to solve finite state/action, infinite-horizon, risk-aware Markov decision processes. Our algorithm has two loops. The inner loop computes the risk by solving a stochastic saddle-point problem. The outer loop performs QQQ-learning to compute an optimal risk-aware policy. Several widely investigated risk measures (e.g. conditional value-at-risk, optimized certainty equivalent, and absolute semi-deviation) are covered by our algorithm. Almost sure convergence and the convergence rate of the algorithm are established. For an error tolerance ϵ>0\epsilon>0ϵ>0 for the optimal QQQ-value estimation gap and learning rate k∈(1/2, 1]k\in(1/2,\,1]k∈(1/2,1], the overall convergence rate of our algorithm is Ω((ln⁡(1/δϵ)/ϵ2)1/k+(ln⁡(1/ϵ))1/(1−k))\Omega((\ln(1/\delta\epsilon)/\epsilon^{2})^{1/k}+(\ln(1/\epsilon))^{1/(1-k)})Ω((ln(1/δϵ)/ϵ2)1/k+(ln(1/ϵ))1/(1−k)) with probability at least 1−δ1-\delta1−δ.

View on arXiv
Comments on this paper