NIPS Proceedingsβ

Yinlam Chow

7 Papers

  • DualDICE: Behavior-Agnostic Estimation of Discounted Stationary Distribution Corrections (2019)
  • A Block Coordinate Ascent Algorithm for Mean-Variance Optimization (2018)
  • A Lyapunov-based Approach to Safe Reinforcement Learning (2018)
  • Safe Policy Improvement by Minimizing Robust Baseline Regret (2016)
  • Policy Gradient for Coherent Risk Measures (2015)
  • Risk-Sensitive and Robust Decision-Making: a CVaR Optimization Approach (2015)
  • Algorithms for CVaR Optimization in MDPs (2014)