Martin L. Puterman
Reinforcement Learning · 1978–2018
A researcher in the Science corpus: 8 papers; trusts 1 researcher and is trusted by 946 researchers here, as inferred from the citation graph.
Subfields
- Reinforcement Learning — 5 citations into it; #20 of 2,242 by trust here, #115 by citations
Whom Martin L. Puterman trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
Who trusts Martin L. Puterman overall
- Craig Boutilier
- Lihong Li
- Michael L. Littman
- Matthew E. Taylor
- R´emi Munos
- Ofir Nachum
- Bo Dai
- Hado van Hasselt
- Sergey Levine
- Peter Stone
Papers from Martin L. Puterman's perspective
Ordered by how strongly the researchers Martin L. Puterman trusts endorse each paper. Same corpus, a different order for every researcher.
- Dynamic Programming and Markov Processes
- Modified Policy Iteration Algorithms for Discounted Markov Decision Problems
- Reinforcement learning
- Exact finite approximations of average-cost countable Markov decision processes
- The Linear Programming Approach to Approximate Dynamic Programming
- OUTPATIENT SCHEDULING IN HEALTH CARE: A REVIEW OF LITERATURE
- A Sequential Bounding Approach for Optimal Appointment Scheduling
- Managing Patient Service in a Diagnostic Medical Facility (Operational Research)
- Temporal Difference Learning and TD-Gammon
- Learning to predict by the methods of temporal differences
Their papers
- Dynamic Programming (2018) — 7,395 citations
- Encyclopedia of Machine Learning and Data Mining (2017) — 452 citations
- Deep Belief Networks (2010) — 380 citations
- Dynamic Multipriority Patient Scheduling for a Diagnostic Resource (2008) — 404 citations
- Markov Decision Processes: Discrete Stochastic Dynamic Programming (1994)
- Markov Decision Processes: Discrete Stochastic Dynamic Programming (1994)
- On the Convergence of Policy Iteration in Stationary Dynamic Programming (1979)
- Modified Policy Iteration Algorithms for Discounted Markov Decision Problems (1978)