TY  - RPRT
TI  - Parameterized MDPs and Reinforcement Learning Problems—A Maximum Entropy Principle-Based Framework
AU  - Srivastava, Amber
AU  - Salapaka, Srinivasa M.
PY  - 2022
DO  - 10.1109/tcyb.2021.3102510
UR  - https://www.osti.gov/biblio/1980477
ID  - 1980477
ER  -