Jonathan Shock

multi-agent reinforcement learning (2) reinforcement learning (1) zero-shot learning (1) offline reinforcement learning (1) game theory (1) question answering (1) policy learning (1) game ai (1) decision transformer (1) zero-shot evaluation (1) text-based game (1) common-pool resource (1) causal masking (1) baseline evaluation (1) text-based environment (1) benchmark methodology (1) networked system control (1)