When Does Trajectory-Level Supervision Permit Efficient Offline Reinforcement Learning?
Paper • 2606.18531 • Published • 4
Xuanfei Ren
xuanfeiren
AI & ML interests
RL and LLM
Recent Activity
commentedon a paper 12 days ago
When Does Trajectory-Level Supervision Permit Efficient Offline Reinforcement Learning? authored a paper 12 days ago
When Does Trajectory-Level Supervision Permit Efficient Offline Reinforcement Learning? upvoted a paper 13 days ago
When Does Trajectory-Level Supervision Permit Efficient Offline Reinforcement Learning?Organizations
None yet
upvoted a paper 13 days ago
upvoted a paper about 1 month ago
upvoted 3
papers 3 months ago
Provably Learning from Language Feedback
Paper • 2506.10341 • Published • 9
Understanding the Challenges in Iterative Generative Optimization with LLMs
Paper • 2603.23994 • Published • 29
Breaking the Capability Ceiling of LLM Post-Training by Reintroducing Markov States
Paper • 2603.19987 • Published • 9
upvoted 2
papers 4 months ago
upvoted an article over 1 year ago
Article
Open-source DeepResearch – Freeing our search agents
- +3
m-ric, albertvillanova, merve, thomwolf, clefourrier
• • 1.32k