A Block Coordinate Ascent Algorithm for Mean-Variance Optimization

Abstract

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.

arXiv commentAccepted by NIPS 2018

Cited by in corpus (7)

• Risk-Sensitive Reinforcement Learning: Near-Optimal Risk-Sample Tradeoff in Regret
• Average-Reward Off-Policy Policy Evaluation with Function Approximation
• Risk-Sensitive Deep RL: Variance-Constrained Actor-Critic Provably Finds Globally Optimal Policy
• Mean-Variance Policy Iteration for Risk-Averse Reinforcement Learning
• Mean-Semivariance Policy Optimization via Risk-Averse Reinforcement Learning
• Massive Access in Secure NOMA under Imperfect CSI: Security Guaranteed Sum-Rate Maximization with First-Order Algorithm
• Mean-Variance Efficient Reinforcement Learning with Applications to Dynamic Financial Investment