Marnix Suilen

robust policy (2) uncertain pomdp (2) safe policy improvement (2) partially observable markov decision process (2) policy learning (2) offline reinforcement learning (2) markov decision process (1) nash equilibrium (1) partial observability (1) uncertainty set (1) stochastic game (1) behavior policy (1) temporal logic (1) imprecise probability (1) robust policy synthesis (1) quadratically-constrained quadratic program (1) probabilistic guarantee (1) finite-state controller (1) interval estimation (1) robust pomdp (1)