Steve Hanks

Reinforcement Learning · 1999–2003

A researcher in the Science corpus: 2 papers; trusts 8 researchers and is trusted by 3 researchers here, as inferred from the citation graph.

Subfields

Whom Steve Hanks trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

  1. Dimitri P. Bertsekas
  2. R. Fikes
  3. Marielle Stoelinga
  4. Richard S. Sutton
  5. Craig Boutilier
  6. Andrew Barto
  7. Michael L. Littman
  8. Nils J. Nilsson
  9. Richard Dearden
  10. Martin L. Puterman

Who trusts Steve Hanks overall

  1. Craig Boutilier
  2. Daphne Koller
  3. Carlos Guestrin
  4. Thomas G. Dietterich
  5. Chris HomesParker
  6. Piotr J. Gmytrasiewicz
  7. Carlos Diuk
  8. Michael L. Littman
  9. Christel Baier
  10. Scott Sanner

Papers from Steve Hanks's perspective

Ordered by how strongly the researchers Steve Hanks trusts endorse each paper. Same corpus, a different order for every researcher.

  1. Dynamic Programming and Markov Processes
  2. Dynamic Programming: Deterministic and Stochastic Models
  3. Learning to Act Using Real-Time Dynamic Programming
  4. Modified Policy Iteration Algorithms for Discounted Markov Decision Problems
  5. A Reinforcement Learning Method for Maximizing Undiscounted Rewards
  6. A survey of algorithmic methods for partially observed Markov decision processes
  7. TD-Gammon, a Self-Teaching Backgammon Program, Achieves Master-Level Play
  8. Decision-Theoretic Planning: Structural Assumptions and Computational Leverage
  9. Stochastic dynamic programming with factored representations
  10. Input Generalization in Delayed Reinforcement Learning: An Algorithm and Performance Comparisons

Their papers