arXiv Machine Learning
techCenter
Simple Actors and Deep Critics for Scalable Reinforcement Learningtranslating…
1 min readUnknownarXiv Digital Media
arXiv:2608.26659v1 Announce Type: new
Abstract: Recent progress in offline reinforcement learning (RL) has been driven by expressive generative actors such as diffusion and flow-matching policies, which capture multimodal behavior in offline datasets. However, these actors…