ENTITY Xiaoming Duan

Xiaoming Duan

PulseAugur coverage of Xiaoming Duan — every cluster mentioning Xiaoming Duan across labs, papers, and developer communities, ranked by signal.

Total · 30d

1

1 over 90d

Releases · 30d

0

0 over 90d

Papers · 30d

1

1 over 90d

TIER MIX · 90D

TOPICS

SENTIMENT · 30D

1 day(s) with sentiment data

RECENT · PAGE 1/1 · 1 TOTAL

TOOL · CL_317519 · Oct 23 · 04:00

Reinforcement learning policy gradient methods analyzed for distribution mismatch

This paper analyzes on-policy policy gradient methods in reinforcement learning, focusing on the impact of distribution mismatch. The research establishes global convergence of objective values for tabular direct and so…