Amarildo Likmeta

reinforcement learning (2) uncertainty quantification (2) wasserstein distance (2) imitation learning (1) sim-to-real transfer (1) bayesian inference (1) distributional reinforcement learning (1) inverse reinforcement learning (1) robot learning (1) continuous control (1) batch learning (1) reward function (1) likelihood maximization (1) expert demonstration (1) wasserstein barycenter (1) safe learning (1) directed exploration (1) robotics benchmark (1) real-world deployment (1) sample efficiency (1)