Yongyuan Liang

4

Papers

12

Total Citations

Papers (4)

Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations

Magma: A Foundation Model for Multimodal AI Agents

ACE: Off-Policy Actor-Critic with Causality-Aware Entropy Regularization

Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss