Awesome World Models / arXiv

DreamSmooth: Improving Model-based Reinforcement Learning via Reward Smoothing

作者：作者信息待提取 · 单位：University of California, Berkeley · 来源：General Approaches to World Models · 发布日期：2023 · 分类：8. World Models in the context of Model-Based RL

基于模型的强化学习
新标签打开 AlphaXiv
DreamSmooth: Improving Model-based Reinforcement Learning via Reward Smoothing figure
AlphaXiv 中文概览（可滚动查看）