Xiaohu Li

deep reinforcement learning (1) reinforcement learning (1) adversarial learning (1) reward modeling (1) autonomous driving (1) multi-modal learning (1) model safety (1) distributional reinforcement learning (1) stochastic dominance (1) convergence guarantee (1) generative adversarial network (1) vision-language model (1) autonomous vehicle (1) jailbreak attack (1) aleatoric uncertainty (1) risk measure (1) human-ai interaction (1) wasserstein gradient flow (1) risk-sensitive reinforcement learning (1) particle-based algorithm (1)