Wojciech M. Czarnecki

knowledge distillation (3) deep reinforcement learning (2) policy distillation (2) transfer learning (1) game theory (1) policy gradient (1) function approximation (1) knowledge transfer (1) policy learning (1) nash equilibrium (1) value function (1) temporal-difference learning (1) robust learning (1) zero-sum game (1) entropy regularization (1) algorithm discovery (1) shared policy (1) multitask reinforcement learning (1) neural network (1) multi-agent system (1)