Georg Ostrovski

distributional reinforcement learning (3) deep reinforcement learning (3) sparse reward (2) quantile regression (2) exploration bonus (2) policy optimization (1) image generation (1) representation learning (1) policy learning (1) convergence analysis (1) offline reinforcement learning (1) dynamic programming (1) function approximation (1) variance reduction (1) passive learning (1) stochastic approximation (1) density models (1) value estimation (1) temporal difference (1) policy gradient (1)