Symmetric Reinforcement Learning Loss for Robust Learning on Diverse Tasks and Model Scales

Ju-Seung Byun; Andrew Perrault

2025 ICML ICML 2025

Symmetric Reinforcement Learning Loss for Robust Learning on Diverse Tasks and Model Scales

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

Ju-Seung Byun, Andrew Perrault

Topics

Reinforcement Learning > Methods > Deep RL Reinforcement Learning > Applications > Game AI Artificial Intelligence > Core AI > Large Language Models

Keywords

reinforcement learning reward model cross-entropy loss reverse cross-entropy sa2c symmetric rl loss

Download PDF