Wojciech Czarnecki

reinforcement learning (2) game theory (2) multi-task learning (2) policy gradient (1) curriculum learning (1) knowledge distillation (1) policy learning (1) adversarial training (1) deep learning (1) knowledge base (1) nash equilibrium (1) value function estimation (1) value estimation (1) zero-sum game (1) atari game (1) game ai (1) progressive training (1) value-based method (1) minimax theorem (1) non-convex game (1)