Chin Pang Ho

Reinforcement Learning (1)

robust markov decision process (6) ambiguity set (5) robust optimization (4) bellman update (3) reinforcement learning (2) policy iteration (2) homotopy continuation (2) markov decision process (2) optimization algorithm (2) best arm identification (1) distributionally robust optimization (1) knowledge gradient (1) asymptotic optimality (1) bellman operator (1) multi-armed bandit (1) transition kernel (1) bandit algorithm (1) first-order method (1) mixed-integer linear programming (1) simplex projection (1)