Katia P. Sycara

multi-agent reinforcement learning (1) reinforcement learning (1) sample efficiency (1) benchmark evaluation (1) policy optimization (1) multimodal learning (1) policy learning (1) reinforcement learning from human feedback (1) policy iteration (1) continuous control (1) concept learning (1) human feedback (1) language model (1) reward model (1) vision-language model (1) zero-shot generalization (1) hallucination mitigation (1) adversarial imitation learning (1) policy model (1) part segmentation (1)