DOSER detects OOD actions via diffusion-model denoising error and applies selective regularization based on predicted transitions, proving gamma-contraction with performance bounds and outperforming priors on offline RL benchmarks.
Linjiajie Fang, Ruoxue Liu, Jing Zhang, Wenjia Wang, and Bing-Yi Jing
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2representative citing papers
EXPO stabilizes online RL for expressive policies by training a base policy with imitation and using a lightweight Gaussian edit policy to select higher-value actions on the fly for sampling and TD backups.
citing papers explorer
-
Beyond Penalization: Diffusion-based Out-of-Distribution Detection and Selective Regularization in Offline Reinforcement Learning
DOSER detects OOD actions via diffusion-model denoising error and applies selective regularization based on predicted transitions, proving gamma-contraction with performance bounds and outperforming priors on offline RL benchmarks.
-
EXPO: Stable Reinforcement Learning with Expressive Policies
EXPO stabilizes online RL for expressive policies by training a base policy with imitation and using a lightweight Gaussian edit policy to select higher-value actions on the fly for sampling and TD backups.