Skip to content
conftrace_
2024 ICML ICML 2024

Reward Model Learning vs. Direct Policy Optimization: A Comparative Analysis of Learning from Human Preferences

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Reinforcement Learning

Authors

Andi Nika, Debmalya Mandal, Parameswaran Kamalaruban, Georgios Tzannetos, Goran Radanovic, Adish Singla

Topics

Machine Learning > Optimization & Theory > Optimization Reinforcement Learning > Methods > Policy Learning

Keywords

direct preference optimization policy learning reward model log-linear policy rlhf linear reward
Download PDF