NeurIPS-2021-understanding-end-to-end-model-based-reinforcement-learning-methods-as-implicit-parameterization-Supplemental.pdf

Open with Kami

Understanding End-to-End Model-Based Reinforcement Learning Methods as Implicit Parameterization Clement Gehring Electrical Engineering and Computer Sciences Massachusetts Institute of Technology clement@gehring.io Kenji Kawaguchi Center of Mathematical Sciences and Applications Harvard University…

saved by

• Vero Chelu

related reading

• NL.pdfabehrouz.github.io
• [2605.01172] A Theory of Generalization in Deep Learningarxiv.org
• [2101.12176] On the Origin of Implicit Regularization in Stochastic Gradient Descentarxiv.org
• [2604.21691] There Will Be a Scientific Theory of Deep Learningarxiv.org
• Reinforcement Learning in Newcomblike Problemsproceedings.neurips.cc
• arxiv.org/pdf/1805.08522arxiv.org
• [2011.01859] A Study of Policy Gradient on a Class of Exactly Solvable Modelsarxiv.org
• Understanding deep learning requires rethinking generalizationarxiv.org
• c21f4ce780c5c9d774f79841b81fdc6d-Paper.pdfproceedings.neurips.cc
• Reinforcement Learning via Implicit Imitation Guidancearxiv.org
• [1707.06347] Proximal Policy Optimization Algorithmsarxiv.org
• [2602.11399] Can We Really Learn One Representation to Optimize All Rewards?arxiv.org