Max Jaderberg

reinforcement learning (2) game theory (2) multi-agent system (2) knowledge distillation (2) neural network architecture (2) nash equilibrium (2) zero-sum game (2) neural network (2) synthetic gradient (2) multi-task learning (2) image classification (1) feature extraction (1) policy gradient (1) probabilistic inference (1) sequence modeling (1) unsupervised learning (1) neural network training (1) model architecture (1) transformer architecture (1) knowledge transfer (1)