Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
Failure Modes of Maximum Entropy RLHF
Ömer Veysel Çağatan, Barış Akgün
In this paper, we show that Simple Preference Optimization (SimPO) can be derived as Maximum Entropy Reinforcement Learning, providing a theoretical foundation for this reference-f…
cs.LG2024
Uncovering RL Integration in SSL Loss: Objective-Specific Implications for Data-Efficient RL
Ömer Veysel Çağatan, Barış Akgün
In this study, we investigate the effect of SSL objective modifications within the SPR framework, focusing on specific adjustments such as terminal state masking and prioritized re…