Navdeep Kumar

Reinforcement Learning (6) Methods (5) Machine Learning (4) Optimization & Theory (4) Applications (3) Learning Types (2) Mathematics & Optimization (1) Optimization (1)

policy gradient (3) robust markov decision process (2) robust mdp (2) global convergence (1) policy learning (1) markov decision process (1) value function (1) reward function (1) finite-time analysis (1) robust markov decision processes (1) transition uncertainty (1) frequency regularization (1) non-rectangular uncertainty (1) average-reward markov decision process (1) robust value function (1) conic hypersurface (1) state-wise decomposition (1) policy visitation (1) worst occupation measure (1) robust q-value (1)