MIL - The University of Tennessee
the university of tennessee machine intelligence lab
  
Zhenzhen Liu, Ph.D (Senior SW engineer at Google, Menlo Park, CA)
  
Call me! Skype
  
Research Reinforcement Learning and Approximate Dynamic Programming 
  
  Reinforcement Learning and Approximate Dynamic Programming
  My work has been on hardware-efficient reinforcement learning algorithms and architectures. I studied both tabular as well as Neurodynamic architectures that lend themselves to hardware implementations on reconfigurable computing platforms.
  
Selected Publications
  
[1]     I. Elhanany, C. Niedzwiedz, Z. Liu, S. Livingston, "A Consolidated Actor-Critic Model for Partially-Observable Markov Decision Processes," IET Electronics Letters, October, 2008 [pdf]
[2]     Z. Liu, I. Elhanany, "A Fast and Scalable Recurrent Neural Network based on Stochastic Meta-Descent," IEEE Transactions on Neural Networks, Vol. 19, No. 9, pp. 1651-1657, September, 2008 [pdf]
[3]     C. Niedzwiedz, I. Elhanany, Z. Liu, S. Livingston, "A Consolidated Actor-Critic Model with Function Approximation for High-Dimensional POMDPs," AAAI 2008 workshop for Advancement in POMDP Solvers (part of the AAAI 2008 Conference), Chicago, July, 2008 [pdf]
[4]     C. Niedzwiedz, Z. Liu, I. Elhanany, S. Livingston, "A Consolidated Actor-Critic Model for Temporal Difference Learning with Function Approximation and Application to POMDPs," 3rd Northeast Student Colloquium on Artificial Intelligence, May, 2008 [pdf]
[5]     Z. Liu, I. Elhanany, "Large-Scale Tabular-Form Hardware Architecture for Q-Learning with Delays," 2007 IEEE Midwest Symposium on Circuits and Systems (MWSCAS), August, 2007
[6]     Z. Liu, I. Elhanany, "Fast and Scalable Recurrent Neural Network Learning based on Stochastic Meta-Descent," Proc. of 26th American Control Conference (ACC), New York City, July, 2007
[7]     Z. Liu, I. Elhanany, "A Scalable Recurrent Neural Network Framework for Model-Free POMDPs," 2007 IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning (ADPRL), April, 2007 [pdf]
[8]     Z. Liu, I. Elhanany, "RL-MAC: A QoS-Aware Reinforcement Learning based MAC Protocol for Wireless Sensor Networks," IEEE Conference on Networking, Sensing and Control, Ft. Lauderdale, FL, April, 2006 [pdf]
[9]     Z. Liu, I. Elhanany, "RL-MAC: A Reinforcement Learning based MAC Protocol for Wireless Sensor Networks," International Journal of Sensor Networks (IJSNet), Vol. 1, No. 2, April, 2006 [pdf]