Huy Hoang

imitation learning (1) convex optimization (1) constrained reinforcement learning (1) policy learning (1) inverse reinforcement learning (1) behavior cloning (1) reward learning (1) safe reinforcement learning (1) primal-dual method (1) distributed consensus (1) shared log (1) cost constraint (1) conditional value at risk (1) offline imitation learning (1) state augmentation (1) value at risk (1) safe policy (1) constrained rl (1) reward penalty (1) virtual log (1)