2 papers
cs.LG2026
Diagnosing Training Inference Mismatch in LLM Reinforcement Learning
Tianle Zhong, Neiwen Ling, Yifan Pi +5
Modern LLM RL systems separate rollout generation from policy optimization. These two stages are expected to produce token probabilities that match exactly. However, implementation…
cs.LG2026
AdaGamma: State-Dependent Discounting for Temporal Adaptation in Reinforcement Learning
Yaomin Wang, Jianting Pan, Ran Tian +4
The discount factor in reinforcement learning controls both the effective planning horizon and the strength of bootstrapping, yet most deep RL methods use a single fixed value acro…