Approximation benefits of policy gradient methods with aggregated states
Year of publication: |
2023
|
---|---|
Authors: | Russo, Daniel |
Published in: |
Management science : journal of the Institute for Operations Research and the Management Sciences. - Hanover, Md. : INFORMS, ISSN 1526-5501, ZDB-ID 2023019-9. - Vol. 69.2023, 11, p. 6898-6911
|
Subject: | approximate dynamic programming | policy gradient methods | reinforcement learning | state aggregation | Theorie | Theory | Mathematische Optimierung | Mathematical programming | Dynamische Optimierung | Dynamic programming | Aggregation |
-
A low-rank approximation for MDPs via moment coupling
Zhang, Amy B. Z., (2024)
-
Efficient reinforcement learning in deterministic systems with value function generalization
Wen, Zheng, (2017)
-
Heitmann, Reinhold-Julius Otto, (2024)
- More ...
-
Learning to optimize via posterior sampling
Russo, Daniel, (2014)
-
A finite time analysis of temporal difference learning with linear function approximation
Bhandari, Jalaj, (2021)
-
On the futility of dynamics in robust mechanism design
Balseiro, Santiago R., (2021)
- More ...