cmu -通过可靠的批评者和与部署一致的数据改进在线政策 Online Policy Improvement via Reliable Critics and Deployment-Aligned Data.pdfVIP

  • 0
  • 0
  • 约14.02万字
  • 约 63页
  • 2026-07-14 发布于广东
  • 举报

cmu -通过可靠的批评者和与部署一致的数据改进在线政策 Online Policy Improvement via Reliable Critics and Deployment-Aligned Data.pdf

OnlinePolicyImprovementvia

ReliableCriticsand

Deployment-AlignedData

HaotianLin

CMU-RI-TR-26-40

May2026

SchoolofComputerScience

TheRoboticsInstitute

CarnegieMellonUniversity

Pittsburgh,Pennsylvania

ThesisCommittee:

GuanyaShi,Co-Chair

JeffSchneider,Co-Chair

您可能关注的文档

文档评论(0)

1亿VIP精品文档

相关文档