Jian Tao

multi-agent reinforcement learning (1) sample efficiency (1) image generation (1) direct preference optimization (1) reinforcement learning from human feedback (1) model-based reinforcement learning (1) novelty detection (1) diffusion model (1) reward model (1) sparse reward (1) cooperative multi-agent (1) intrinsic reward (1) behavioral diversity (1) state novelty (1) large language model (1) random network distillation (1) goal achieving (1) goal-directed exploration (1) sample reuse (1)