Sergey Kolesnikov

offline reinforcement learning (5) deep reinforcement learning (4) uncertainty estimation (2) policy evaluation (1) few-shot learning (1) policy optimization (1) bayesian inference (1) policy learning (1) laplace approximation (1) fisher information (1) value iteration (1) scalable training (1) out-of-distribution detection (1) adaptive agent (1) meta-reinforcement learning (1) task distribution (1) reinforcement learning benchmark (1) scalable computing (1) soft actor-critic (1) multi-task adaptation (1)