Ryan Sullivan

proximal policy optimization (3) policy gradient (2) reinforcement learning (2) preference alignment (1) procedural generation (1) deep learning (1) reinforcement learning from human feedback (1) variance reduction (1) optimization landscape (1) multi-objective optimization (1) policy training (1) parameter-efficient finetuning (1) multi-agent environment (1) inference time (1) multi-task training (1) analytical gradient (1) large language model (1) reward surface (1) reinforcement learning environment (1) multi-agent system (1)