Skill-aware Mutual Information Optimisation for Generalisation in Reinforcement Learning
Paper • 2406.04815 • Published
Xuehui Yu
yuxuehui
AI & ML interests
Reinforcement Learning/Robotics
Recent Activity
authored a paper 14 days ago
Skill-aware Mutual Information Optimisation for Generalisation in Reinforcement Learning authored a paper 14 days ago
Conflict-Aware Additive Guidance for Flow Models under Compositional Rewards authored a paper 14 days ago
Divide-and-Remember: Recursive Action-Relevant Memory for Long-Horizon VLA PoliciesOrganizations
authored 3
papers 14 days ago
upvoted a paper 14 days ago
published 2
models 5 months ago
published 3
datasets 5 months ago