Off-Dynamics Reinforcement Learning via Domain Adaptation and Reward Augmented Imitation
Paper • 2411.09891 • Published
Yixuan Wang
noMushroom
·
AI & ML interests
Interpretability, Machine Learning Theory, Generative Modeling, World Model, Reinforcement Learning
Recent Activity
authored a paper 9 days ago
Off-Dynamics Reinforcement Learning via Domain Adaptation and Reward Augmented Imitation authored a paper 9 days ago
Skeletons in Flow: Graph Structured Flow Matching for Human Motion Prediction authored a paper 9 days ago
Effective Model Pruning: Measure The Redundancy of Model ComponentsOrganizations
authored 5
papers 9 days ago
Skeletons in Flow: Graph Structured Flow Matching for Human Motion Prediction
Paper • 2609.32231 • Published
Effective Model Pruning: Measure The Redundancy of Model Components
Paper • 2509.25606 • Published
Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization
Paper • 2608.16072 • Published • 30
Riemannian Lyapunov Optimizer: A Unified Framework for Optimization
Paper • 2601.22284 • Published