Mihailo Jovanovic

regret bound (2) function approximation (2) policy optimization (2) primal-dual optimization (1) constrained optimization (1) markov decision process (1) nash equilibrium (1) constrained markov decision process (1) safe reinforcement learning (1) convergence guarantee (1) zero-sum game (1) primal-dual method (1) lagrangian method (1) markov potential game (1) safe exploration (1) occupancy measure (1) multi-agent reinforcement learning (1) constrained markov game (1) policy gradient (1) natural policy gradient (1)