北京
分享至
论文《Act More， Decide Less》提出SPACE方法，从成功轨迹中归纳两级程序化技能，并以子技能边界作为块边界进行监督。随后，通过混合on/off-policy优化与chunk-aware credit assignment技术，蒸馏出primitive-chunk策略。
特别声明：以上内容(如有图片或视频亦包括在内)为自媒体平台“网易号”用户上传并发布，本平台仅提供信息存储服务。
Notice: The content above (including the pictures and videos if any) is uploaded and posted by a user of NetEase Hao, which is a social media platform and only provides information storage services.
