On the theory of policy gradient methods: Optimality, approximation, and distribution shift

Alekh Agarwal, Sham M. Kakade, Jason D. Lee, Gaurav Mahajan

Research output: Contribution to journalArticlepeer-review

Fingerprint

Dive into the research topics of 'On the theory of policy gradient methods: Optimality, approximation, and distribution shift'. Together they form a unique fingerprint.

Mathematics

Engineering & Materials Science