Elad Sarafian

reinforcement learning (3) policy optimization (2) gradient learning (2) black-box optimization (2) policy gradient (1) kl divergence (1) gradient estimation (1) distribution matching (1) batch learning (1) off-policy learning (1) policy improvement (1) high-dimensional optimization (1) regret bound (1) normalizing flow (1) meta-reinforcement learning (1) data efficiency (1) evolutionary algorithm (1) policy network (1) constrained policy optimization (1) explicit gradient learning (1)