Stephen Giguere

reinforcement learning (1) off-policy evaluation (1) algorithmic fairness (1) offline reinforcement learning (1) risk management (1) sequential decision making (1) policy learning (1) deep learning (1) constrained optimization (1) markov decision process (1) natural gradient (1) natural actor-critic (1) importance sampling (1) policy search (1) natural gradient descent (1) mirror descent (1) offline learning (1) safe reinforcement learning (1) contextual bandit (1) uncertainty estimation (1)