Timezone: »

 
Poster
A Block Coordinate Ascent Algorithm for Mean-Variance Optimization
Tengyang Xie · Bo Liu · Yangyang Xu · Mohammad Ghavamzadeh · Yinlam Chow · Daoming Lyu · Daesub Yoon

Wed Dec 05 07:45 AM -- 09:45 AM (PST) @ Room 517 AB #162
in Wed Poster Session A »

Risk management in dynamic decision problems is a primary concern in many fields, including financial investment, autonomous driving, and healthcare. The mean-variance function is one of the most widely used objective functions in risk management due to its simplicity and interpretability. Existing algorithms for mean-variance optimization are based on multi-time-scale stochastic approximation, whose learning rate schedules are often hard to tune, and have only asymptotic convergence proof. In this paper, we develop a model-free policy search framework for mean-variance optimization with finite-sample error bound analysis (to local optima). Our starting point is a reformulation of the original mean-variance function with its Fenchel dual, from which we propose a stochastic block coordinate ascent policy search algorithm. Both the asymptotic convergence guarantee of the last iteration's solution and the convergence rate of the randomly picked solution are provided, and their applicability is demonstrated on several benchmark domains.

Keywords: Reinforcement Learning and Planning · Decision and Control · Reinforcement Learning · Markov Decision Processes
[ Paper]  [ Poster] 

Author Information

Tengyang Xie (University of Massachusetts Amherst)
Bo Liu (Auburn University)
Yangyang Xu (Rensselaer Polytechnic Institute)
Mohammad Ghavamzadeh (Facebook AI Research)
Yinlam Chow (DeepMind)
Daoming Lyu (Auburn University)
Daesub Yoon (ETRI)

More from the Same Authors