Free from Bellman Completeness: Trajectory Stitching via Model-based Return-conditioned Supervised Learning
Paper
•
2310.19308
•
Published
Runlong Zhou
vectorzhou
AI & ML interests
None yet
Recent Activity
liked
a dataset
7 days ago
RUC-AIBOX/ICPC-Eval
updated
a dataset
17 days ago
vectorzhou/MATH_500_L5_Qwen3_235B_A22B_Temp_1.0_L_16384
updated
a dataset
17 days ago
vectorzhou/MATH_500_L5_DeepSeek_R1_0528_Temp_1.0_L_16384
Organizations
authored
4
papers
5 months ago
Horizon-Free and Variance-Dependent Reinforcement Learning for Latent Markov Decision Processes
Paper
•
2210.11604
•
Published
Multi-Agent Reinforcement Learning from Human Feedback: Data Coverage and Algorithmic Techniques
Paper
•
2409.00717
•
Published
Extragradient Preference Optimization (EGPO): Beyond Last-Iterate Convergence for Nash Learning from Human Feedback
Paper
•
2503.08942
•
Published