Q-learning for Markov decision processes with a satisfiability criterion

Suhail M. Shah, Vivek S. Borkar. Q-learning for Markov decision processes with a satisfiability criterion. Systems & Control Letters, 113:45-51, 2018. [doi]

Authors

Suhail M. Shah

This author has not been identified. Look up 'Suhail M. Shah' in Google

Vivek S. Borkar

This author has not been identified. Look up 'Vivek S. Borkar' in Google