Rati Devidze

Applications (2) Privacy (1)

reinforcement learning (4) inverse reinforcement learning (3) policy learning (2) sparse reward (2) reward function (2) reward shaping (2) environment poisoning (2) policy teaching (2) optimal policy (2) curriculum learning (1) markov decision process (1) policy optimization (1) multi-agent reinforcement learning (1) knowledge transfer (1) online learning (1) adversarial attack (1) machine teaching (1) self-supervised learning (1) regret bound (1) collaborative learning (1)