Raphael Koster

social dilemma (2) multi-agent reinforcement learning (2) few-shot learning (1) decision making (1) uncertainty quantification (1) multimodal learning (1) video understanding (1) ai safety (1) machine learning (1) selective prediction (1) human-ai collaboration (1) markov game (1) evaluation benchmark (1) deferral learning (1) learning to defer (1) human-ai interaction (1) scenario generation (1) cooperative behavior (1) composite accuracy (1) test scenario (1)