Esther Derman

robust markov decision process (3) policy gradient (2) model misspecification (1) robust reinforcement learning (1) markov decision process (1) value function (1) policy iteration (1) reward function (1) uncertainty set (1) deep q-network (1) safe exploration (1) frequency regularization (1) non-rectangular uncertainty (1) uncertainty robust bellman equation (1) regularized mdp (1) policy visitation (1) worst occupation measure (1) robust q-value (1) robust optimization (1) rectangular robustness (1)