Home * People * A. Harry Klopf
AHKlopf.jpg

A. Harry Klopf,
an American senior scientist for machine intelligence, since the early 70s affiliated with the Avionics Directorate, Wright Laboratory and Air Force Research Laboratory, Aeronautical Systems Center, Wright-Patterson Air Force Base, Ohio. His research focused on reinforcement learning, and adaptive behavior as approaches to the analysis of natural intelligence and the synthesis of machine intelligence [1]. Temporal difference learning has one root in Klopf's work on animal learning psychology [2] - beside Arthur Samuel's pioneering work on his self learning Checkers player in the late 50s [3] [4].
A. Harry Klopf [5]

Selected Publications

[6]

1970 ...

1980 ...

1990 ...

2000 ...


References

  1. ^ "About the Authors" from Leemon C. Baird III, Mance E. Harmon, A. Harry Klopf (1996). Reinforcement Learning: An Alternative Approach to Machine Intelligence. pdf
  2. ^ A. Harry Klopf (1972). Brain Function and Adaptive Systems - A Heterostatic Theory. Air Force Cambridge Research Laboratories, Special Reports, No. 133, pdf
  3. ^ Arthur Samuel (1959). Some Studies in Machine Learning Using the Game of Checkers. IBM Journal July 1959
  4. ^ Richard Sutton, Andrew Barto (1998). Reinforcement Learning: An Introduction. MIT Press, 6.10 Bibliographical and Historical Remarks
  5. ^ Image from Leemon C. Baird III, Mance E. Harmon, A. Harry Klopf (1996). Reinforcement Learning: An Alternative Approach to Machine Intelligence. pdf
  6. ^ dblp: A. Harry Klopf
  7. ^ Heterostasis from Wikipedia
  8. ^ Hedonism from Wikipedia
  9. ^ Classical conditioning from Wikipedia

What links here?


Up one level