Ruijie Zheng

8

Papers

32

Total Citations

Papers (8)

COPlanner: Plan to Roll Out Conservatively but to Explore Optimistically for Model-Based RL

Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations

A Forget-and-Grow Strategy for Deep Reinforcement Learning Scaling in Continuous Control

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

Magma: A Foundation Model for Multimodal AI Agents

PRISE: LLM-Style Sequence Compression for Learning Temporal Action Abstractions in Control

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

Adapting Static Fairness to Sequential Decision-Making: Bias Mitigation Strategies towards Equal Long-term Benefit Rate