Parameterized MDPs and Reinforcement Learning Problems - A Maximum Entropy Principle-Based Framework

Amber Srivastava, Srinivasa M. Salapaka. Parameterized MDPs and Reinforcement Learning Problems - A Maximum Entropy Principle-Based Framework. IEEE T. Cybernetics, 52(9):9339-9351, 2022. [doi]

Authors

Amber Srivastava

This author has not been identified. Look up 'Amber Srivastava' in Google

Srinivasa M. Salapaka

This author has not been identified. Look up 'Srinivasa M. Salapaka' in Google