Boris Belousov

reinforcement learning (3) offline reinforcement learning (1) partially observable markov decision process (1) probabilistic modeling (1) sim-to-real transfer (1) bayesian inference (1) curriculum learning (1) likelihood-free inference (1) graph representation (1) domain randomization (1) posterior distribution (1) value function (1) value iteration (1) system identification (1) sequential decision-making (1) exploration exploitation (1) trajectory optimization (1) relative entropy (1) optimal value function (1) sample efficiency (1)