Jia-Hong Wu

E-mail: jw@alumni.purdue.edu

I got my PhD in the school of Electrical and Computer Engineering at Purdue University, West Lafayette. My advisor is Professor Givan.

Topics of my doctoral dissertation:

• Learning useful heuristic functions in stochastic planning via automatic feature induction
• Stochastic planning via local search (Stochastic Enforced Hill-Climbing)

Research Interest

• Designing novel computational algorithms for Decision-Theoretic Planning and Machine Learning
• Utilizing Knowledge Representation and Knowledge Change in relevant fields such as Planning, Control, Machine Learning, Security
• Applications of Planning and Learning in other research fields such as Security, Computer Networking, Signal Processing, Computer Architecture, Psychology, and Education
• Other relevant topics in Artificial Intelligence, Optimal Control, Markov Decision Processes, Computational Algorithm, Pattern Recognition, Image Processing, Neural Network

Publications

• Probabilistic Planning via Automatic Feature Induction and Stochastic Enforced Hill-Climbing
  Doctoral dissertation
  PDF
• Stochastic Enforced Hill-Climbing
  Jia-Hong Wu, Rajesh Kalyanam, and Robert Givan
  In Proceedings of the Eighteenth International Conference on Automated Planning and Scheduling, pp. 396-403, 2008 (ICAPS 2008)
  PDF
• Discovering Relational Domain Features for Probabilistic Planning
  Jia-Hong Wu and Robert Givan
  In Proceedings of the Seventeenth International Conference on Automated Planning and Scheduling, pp. 344-351, 2007 (ICAPS 2007)
  PDF
• Feature-discovering Approximate Value Iteration Methods
  Jia-Hong Wu and Robert Givan
  In Proceedings of the 6th International Symposium on Abstraction, Reformulation, and Approximation, pp. 321-331, 2005 (SARA 2005)
  
• Feature-discovering Approximate Value Iteration Methods
  Jia-Hong Wu and Robert Givan
  Purdue ECE Technical report TR-ECE-04-06, November 2004
  PDF