Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF
Paper • 2410.04612 • Published
Databricks
company
Verified
AI & ML interests
None defined yet.
Papers
OfficeQA Pro: An Enterprise Benchmark for End-to-End Grounded Reasoning
KARL: Knowledge Agents via Reinforcement Learning
Your employees were clearly bored
👍🤗 2
3
#18 opened about 1 year ago
by 
ChuckMcSneed
whzhan
authored a
paper over 1 year ago
whzhan
authored 5
papers almost 2 years ago
Provably Efficient CVaR RL in Low-rank MDPs
Paper • 2311.11965 • Published
REBEL: Reinforcement Learning via Regressing Relative Rewards
Paper • 2404.16767 • Published • 2
Provable Offline Preference-Based Reinforcement Learning
Paper • 2305.14816 • Published
Provable Reward-Agnostic Preference-Based Reinforcement Learning
Paper • 2305.18505 • Published
Dataset Reset Policy Optimization for RLHF
Paper • 2404.08495 • Published • 9
matthayes
updated a
dataset almost 3 years ago