Stale but Stable: Staleness-Adaptive Trust Regions for Stabilizing Asynchronous Reinforcement Learning
Paper • 2607.18722 • Published • 31
🤝 Open to Collab
Lei ZHU
rayleizhu
·
AI & ML interests
Sparse Attention, Inference Acceleration, Algorithm-System Co-Design, Parallel Computing
Recent Activity
upvoted an article 7 days ago
Welcome Inkling by Thinking Machines upvoted a paper 8 days ago
Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and EditableOrganizations
None yet
upvoted a paper 2 days ago
upvoted an article 7 days ago
Article
Welcome Inkling by Thinking Machines
- +2
burtenshaw, merve, pcuenq, ariG23498
• • 117 upvoted a paper 8 days ago
upvoted a paper 16 days ago
upvoted an article 7 months ago
Article
A failed experiment: Infini-Attention, and why we should keep trying?
- +1
neuralink, lvwerra, thomwolf
• • 76