---
title: "Machine Learning 1996 — all accepted papers — Elamur Research"
description: "All 83 papers of Machine Learning 1996, the most cited first; those with our summary link to it."
canonical: "https://research.elamur.ai/free/en/venues/machine-learning/1996/papers/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/venues/machine-learning/1996/papers/)

[home](https://md.research.elamur.ai/free/en/) / [venues](https://md.research.elamur.ai/free/en/venues/) / [Machine Learning](https://md.research.elamur.ai/free/en/venues/machine-learning/) / [1996](https://md.research.elamur.ai/free/en/venues/machine-learning/1996/) / papers

# Machine Learning 1996: all accepted papers

83 papers · the most cited first · [← Machine Learning 1996](https://md.research.elamur.ai/free/en/venues/machine-learning/1996/)

1. **[Bagging Predictors ↗](https://doi.org/10.1023/a:1018054314350)**Leo Breiman*17,218 citations*
2. **[Bagging predictors](https://md.research.elamur.ai/free/en/papers/breiman-1996-bagging-predictors/)**Leo Breiman*16,310 citations · our summary*
3. **[Stacked Regressions ↗](https://doi.org/10.1007/bf00117832)**Leo Breiman*1,912 citations*
4. **[Learning in the Presence of Concept Drift and Hidden Contexts ↗](https://doi.org/10.1007/bf00116900)**Gerhard Widmer, Miroslav Kubát*1,840 citations*
5. **[Linear Least-Squares algorithms for temporal difference learning ↗](https://doi.org/10.1007/bf00114723)**Steven J. Bradtke, Andrew G. Barto*599 citations*
6. **[Reinforcement learning with replacing eligibility traces ↗](https://doi.org/10.1007/bf00114726)**Satinder Pal Singh, Richard S. Sutton*575 citations*
7. **[Feature-based methods for large scale dynamic programming ↗](https://doi.org/10.1007/bf00114724)**John N. Tsitsiklis, Benjamin Van Roy*432 citations*
8. **[Average reward reinforcement learning: Foundations, algorithms, and empirical results ↗](https://doi.org/10.1007/bf00114727)**Sridhar Mahadevan*385 citations*
9. **[Efficient reinforcement learning through symbiotic evolution ↗](https://doi.org/10.1007/bf00114722)**David E. Moriarty, Risto P Miikkulainen*325 citations*
10. **[A Lattice Conceptual Clustering System and Its Application to Browsing Retrieval ↗](https://doi.org/10.1007/bf00058654)**Claudio Carpineto, Giovanni Romano*309 citations*
11. **[Incremental multi-step Q-learning ↗](https://doi.org/10.1007/bf00114731)**Jing Peng, Ronald J. Williams*286 citations*
12. **[Purposive behavior acquisition for a real robot by vision-based reinforcement learning ↗](https://doi.org/10.1007/bf00117447)**Minoru Asada, Shoichi Noda, Sukoya Tawaratsumida et al.*274 citations*
13. **[Technical Note: Some Properties of Splitting Criteria ↗](https://doi.org/10.1007/bf00117831)**Leo Breiman*270 citations*
14. **[Unifying Instance-Based and Rule-Based Induction ↗](https://doi.org/10.1007/bf00058656)**Pedro Domingos*242 citations*
15. **[The Power of Amnesia: Learning Probabilistic Automata with Variable Memory Length ↗](https://doi.org/10.1023/a:1026490906255)**Dana Ron, Yoram Singer, Naftali Tishby*185 citations*
16. **[Error reduction through learning multiple descriptions ↗](https://doi.org/10.1007/bf00058611)**Kamal Ali, Michael J. Pazzani*163 citations*
17. **[Exploration Bonuses and Dual Control ↗](https://doi.org/10.1007/bf00115298)**Peter Dayan, Terrence J. Sejnowski*118 citations*
18. **[The effect of representation and knowledge on goal-directed exploration with reinforcement-learning algorithms ↗](https://doi.org/10.1007/bf00114729)**Sven Koenig, Reid G. Simmons*102 citations*
19. **[Creating advice-taking reinforcement learners ↗](https://doi.org/10.1007/bf00114730)**Richard Maclin, JUDE W. SHAVLIK*98 citations*
20. **[Representation of Finite State Automata in Recurrent Radial Basis Function Networks ↗](https://doi.org/10.1007/bf00116897)**Paolo Frasconi, Marco Gori, Marco Maggini et al.*97 citations*
21. **[Robot programming by Demonstration (RPD): Supporting the induction by human interaction ↗](https://doi.org/10.1007/bf00117443)**H. Friedrich, S. M�nch, Rüdiger Dillmann et al.*77 citations*
22. **[On-line Prediction and Conversion Strategies ↗](https://doi.org/10.1007/bf00115301)**Nicolò Cesa‐Bianchi, Yoav Freund, David P. Helmbold et al.*72 citations*
23. **[Scaling Up Inductive Learning with Massive Parallelism ↗](https://doi.org/10.1007/bf00116898)**Foster John Provost, John M. Aronis*56 citations*
24. **[Active learning for vision-based robot grasping ↗](https://doi.org/10.1007/bf00117446)**Marcos Salganicoff, Lyle Ungar, Ruzena Bajcsy*51 citations*
25. **[BEXA: A Covering Algorithm for Learning Propositional Concept Descriptions ↗](https://doi.org/10.1007/bf00117830)**H Theron, Ian Cloete*44 citations*
26. **[Learning concepts from sensor data of a mobile robot ↗](https://doi.org/10.1007/bf00117448)**Volker Klingspor, Katharina J. Morik, Anke D. Rieger*44 citations*
27. **[Linear Least-Squares Algorithms for Temporal Difference Learning ↗](https://doi.org/10.1023/a:1018056104778)**Steven J. Bradtke, Andrew G. Barto*39 citations*
28. **[Classification by Feature Partitioning ↗](https://doi.org/10.1007/bf00116899)**Halil Altay Güvenir, İzzet Şirin*36 citations*
29. **[Efficient incremental induction of decision trees ↗](https://doi.org/10.1007/bf00058613)**Dimitris Kalles, Tim Morris*36 citations*
30. **[On the worst-case analysis of temporal-difference learning algorithms ↗](https://doi.org/10.1007/bf00114725)**Robert E. Schapire, Manfred K. Warmuth*33 citations*
31. **[Reinforcement Learning with Replacing Eligibility Traces ↗](https://doi.org/10.1023/a:1018012322525)**Satinder Pal Singh, Richard S. Sutton*28 citations*
32. **[Using the Minimum Description Length Principle to Infer Reduced Ordered Decision Graphs ↗](https://doi.org/10.1007/bf00115299)**Arlindo L. Oliveira, Alberto Luigi Sangiovanni-Vincentelli*27 citations*
33. **[Average Reward Reinforcement Learning: Foundations, Algorithms, and Empirical Results ↗](https://doi.org/10.1023/a:1018064306595)**Sridhar Mahadevan*26 citations*
34. **[Classic Learning ↗](https://doi.org/10.1023/a:1026443024002)**Michael Frazier, Leonard Pitt*25 citations*
35. **[Learning controllers for industrial robots ↗](https://doi.org/10.1007/bf00117445)**Cristina Baroglio A, Attilio Giordana, M. Kaiser et al.*23 citations*
36. **[Rigorous Learning Curve Bounds from Statistical Mechanics ↗](https://doi.org/10.1023/a:1026499208981)**David H. Haussler, Michael J. Kearns, H. Sebastian Seung et al.*20 citations*
37. **[Real-world robotics: Learning to plan for robust execution ↗](https://doi.org/10.1007/bf00117442)**Scott W. Bennett, GERALD F. DEJONG*19 citations*
38. **[A decision-tree model of balance scale development ↗](https://doi.org/10.1007/bf00058612)**William C. Schmidt, Charles X. Ling*18 citations*
39. **[The loss from imperfect value functions in expectation-based and minimax-based tasks ↗](https://doi.org/10.1007/bf00114728)**Matthias Heger*18 citations*
40. **[Performance improvement of robot continuous-path operation through iterative learning using neural networks ↗](https://doi.org/10.1007/bf00117444)**Peter C. Y. Chen, James K. Mills, Kenneth C. Smith*16 citations*
41. **[Feature-Based Methods for Large Scale Dynamic Programming ↗](https://doi.org/10.1023/a:1018008221616)**John N. Tsitsiklis, Benjamin Van Roy*15 citations*
42. **[On Learning Visual Concepts and DNF Formulae ↗](https://doi.org/10.1023/a:1018098129371)**Eyal Kushilevitz Z, Dan Roth*10 citations*
43. **[On the Limits of Proper Learnability of Subclasses of DNF Formulas ↗](https://doi.org/10.1023/a:1026455409889)**Krishnan Pillaipakkamnatt, Vijay Raghavan*9 citations*
44. **[PAC Learning of One-Dimensional Patterns ↗](https://doi.org/10.1007/bf00115300)**Paul W. Goldberg, Sally A. Goldman, Stephen Scott*9 citations*
45. **[Efficient Reinforcement Learning through Symbiotic Evolution ↗](https://doi.org/10.1023/a:1018004120707)**David E. Moriarty, Risto Mikkulainen*8 citations*
46. **[Incremental Multi-Step Q-Learning ↗](https://doi.org/10.1023/a:1018076709321)**Jing Peng, Ronald J. Williams*8 citations*
47. **[Creating Advice-Taking Reinforcement Learners ↗](https://doi.org/10.1023/a:1018020625251)**Richard Maclin, JUDE W. SHAVLIK*7 citations*
48. **[On learning visual concepts and DNF formulae ↗](https://doi.org/10.1007/bf00117833)**Eyal Kushilevitz Z, Dan Roth*7 citations*
49. **[Purposive Behavior Acquisition for a Real Robot by Vision-Based Reinforcement Learning ↗](https://doi.org/10.1023/a:1018237008823)**Minoru Asada, Shoichi Noda, Sukoya Tawaratsumida et al.*7 citations*
50. **[Learning Concepts from Sensor Data of a Mobile Robot ↗](https://doi.org/10.1023/a:1018245209731)**Volker Klingspor, Katharina J. Morik, Anke D. Rieger*6 citations*
51. **[Learning Controllers for Industrial Robots ↗](https://doi.org/10.1023/a:1018228822027)**Cristina Baroglio A, Attilio Giordana, Roberto Piola et al.*4 citations*
52. **[The Effect of Representation and Knowledge on Goal-Directed Exploration with Reinforcement-Learning Algorithms ↗](https://doi.org/10.1023/a:1018068507504)**Sven Koenig, Reid G. Simmons*4 citations*
53. **[A Reply to Pazzani's Book Review of "Inductive Logic Programming: Techniques and Applications" ↗](https://doi.org/10.1007/bf00116902)**Nada Lavrač A, Sašo Džeroski*3 citations*
54. **[Introduction ↗](https://doi.org/10.1007/bf00114721)**Leslie Pack Kaelbling*3 citations*
55. **[Editorial ↗](https://doi.org/10.1023/a:1018067001143)**Thomas G. Dietterich*2 citations*
56. **[Editorial ↗](https://doi.org/10.1007/bf00058653)**Thomas G. Dietterich*2 citations*
57. **[Introduction ↗](https://doi.org/10.1023/a:1018091703869)**Leslie Pack Kaelbling*2 citations*
58. **[On the Worst-Case Analysis of Temporal-Difference Learning Algorithms ↗](https://doi.org/10.1023/a:1018060205686)**Robert E. Schapire, Manfred K. Warmuth*2 citations*
59. **[Review of ?Inductive Logic Programming: Techniques and Applications? by Nada Lavra?, Sa?o D?eroski ↗](https://doi.org/10.1007/bf00116901)**Michael J. Pazzani*2 citations*
60. **[Robot Programming by Demonstration (RPD): Supporting the Induction by Human Interaction ↗](https://doi.org/10.1023/a:1018224721118)**H. Friedrich, S. Mnch, R. Dillmann et al.*2 citations*
61. **[Performance Improvement of Robot Continuous-Path Operation through Iterative Learning Using Neural Networks ↗](https://doi.org/10.1023/a:1018276705188)**Peter C. Y. Chen, James K. Mills, Kenneth C. Smith*1 citation*
62. **[Real-World Robotics: Learning to Plan for Robust Execution ↗](https://doi.org/10.1023/a:1018274104280)**Scott W. Bennett, GERALD F. DEJONG*1 citation*
63. **[19種類の中から賃金政策を選択 (特集 企業における高齢者雇用の課題) ↗](http://ci.nii.ac.jp/naid/40004751871)**算織 滝沢
64. **[Active Learning for Vision-Based Robot Grasping ↗](https://doi.org/10.1023/a:1018280807006)**Marcos Salganicoff, Lyle Ungar, Ruzena K. Bajcsy
65. **[Editorial ↗](https://doi.org/10.1007/bf00114720)**
66. **[Guest Editor's Introduction ↗](https://doi.org/10.1023/a:1026466322185)**Thomas Hancock
67. **[Introduction ↗](https://doi.org/10.1007/bf00117441)**
68. **[M字カ-ブ全体が上方シフト 総理府「女性白書」 ↗](http://ci.nii.ac.jp/naid/40004751841)**総理府
69. **[Review of "Inductive Logic Programming: Techniques and Applications" by Nada Lavrač, Sašo Džeroski ↗](https://doi.org/10.1023/a:1018098519027)**Michael J. Pazzani
70. **[The Loss from Imperfect Value Functions in Expectation-Based and Minimax-Based Tasks ↗](https://doi.org/10.1023/a:1018016523433)**Matthias Heger
71. **[上手に利用して大きな成果 労働省「時短奨励金活用事例集」 ↗](http://ci.nii.ac.jp/naid/40004751840)**労働省
72. **[変化に対応した年金制度確立を 厚生省「平成8年版厚生白書」 ↗](https://ci.nii.ac.jp/naid/40004751845)**厚生省
73. **[平均報酬額は社長さんで192万円 — 「社長・重役の報酬・賞与の実態」 ↗](http://ci.nii.ac.jp/naid/40004751851)**賃金管理研究所
74. **[度数率1.88,3年連続マイナスへ 労働省「労働災害動向調査結果」 ↗](http://ci.nii.ac.jp/naid/40004751844)**労働省
75. **[採用後ほぼ6年間は年功運用 日本人事行政研究所「人事管理諸施策に関する調査」 ↗](http://ci.nii.ac.jp/naid/40004751837)**日本人事行政研究所
76. **[時間外の目安は年150時間に 連合「′96・97年の雇用・労働政策要求」 ↗](http://ci.nii.ac.jp/naid/40004751846)**連合
77. **[格差是正や各種支援措置を — 「96・97年の中小企業,男女平等政策要求」 ↗](http://ci.nii.ac.jp/naid/40004751852)**連合
78. **[標準年齢を廃し年功色払拭へ — 「役職・昇進制度に関する調査」 ↗](http://ci.nii.ac.jp/naid/40004751849)**愛知県経営者協会
79. **[沿岸荷役作業員で日額19,730円 — 「屋外労働者職種別賃金(港湾運送)」 ↗](http://ci.nii.ac.jp/naid/40004751850)**労働省
80. **[滋賀の製造業が全国トップに 社会経済生産性本部「県別生産性ランキング」 ↗](http://ci.nii.ac.jp/naid/40004751839)**社会経済生産性本部
81. **[物価の安定で実質賃金2.1%増 — 「平成8年版労働経済の分析」 ↗](http://ci.nii.ac.jp/naid/40004751853)**労働省
82. **[特集 こころの"人間ドック"創設を ↗](http://ci.nii.ac.jp/naid/40004751860)**浩也 久保田
83. **[約9割で雇用コスト削減必要 経済企画庁「企業行動に関する調査」 ↗](http://ci.nii.ac.jp/naid/40004751838)**経済企画庁
- [← back to](https://md.research.elamur.ai/free/en/venues/machine-learning/1996/) — Machine Learning 1996