NIPS Proceedingsβ

Mohammad Ghavamzadeh

12 Papers

  • Safe Policy Improvement by Minimizing Robust Baseline Regret (2016)
  • Policy Gradient for Coherent Risk Measures (2015)
  • Algorithms for CVaR Optimization in MDPs (2014)
  • Actor-Critic Algorithms for Risk-Sensitive MDPs (2013)
  • Approximate Dynamic Programming Finally Performs Well in the Game of Tetris (2013)
  • Best Arm Identification: A Unified Approach to Fixed Budget and Fixed Confidence (2012)
  • Multi-Bandit Best Arm Identification (2011)
  • Speedy Q-Learning (2011)
  • LSTD with Random Projections (2010)
  • Regularized Policy Iteration (2008)
  • Incremental Natural Actor-Critic Algorithms (2007)
  • Bayesian Policy Gradient Algorithms (2006)