1.7k citations · 2k across the 66 of their papers we have counts for
3 papers · 1 filter
MidSteer: Optimal Affine Framework for Steering Generative Models
Tatiana Gaintseva, Andrew Stepanov, Ziquan Liu +4
Steering intermediate representations has emerged as a powerful strategy for controlling generative models, particularly in post-deployment alignment and safety settings. However,…
Partial advantage estimator for proximal policy optimization
Xiulei Song, Yizhao Jin, Greg Slabaugh +1
Estimation of value in policy gradient methods is a fundamental problem. Generalized Advantage Estimation (GAE) is an exponentially-weighted estimator of an advantage function simi…
Joint action loss for proximal policy optimization
Xiulei Song, Yizhao Jin, Greg Slabaugh +1
PPO (Proximal Policy Optimization) is a state-of-the-art policy gradient algorithm that has been successfully applied to complex computer games such as Dota 2 and Honor of Kings. I…