Navdeep Kumar

robust markov decision process (2) policy gradient (2) geometric analysis (1) markov decision process (1) value function (1) reward function (1) robust mdp (1) transition uncertainty (1) frequency regularization (1) non-rectangular uncertainty (1) robust value function (1) conic hypersurface (1) state-wise decomposition (1) policy visitation (1) worst occupation measure (1) robust q-value (1) robust optimization (1) rectangular robustness (1) policy optimization (1)