article Open AccessTop 1% cited
Self-improving reactive agents based on reinforcement learning, planning and teaching
Machine Learning · 1992 · Vol. 8(3-4) · pp. 293–321
Long-Ji Lin✉(Carnegie Mellon University)
Reinforcement Learning in RoboticsEvolutionary Algorithms and ApplicationsAdaptive Dynamic Programming ControlReinforcement learningComputer scienceArtificial intelligenceTestbedNondeterministic algorithmHeuristicGeneralizationLearning classifier systemMachine learningTheoretical computer science
Funding
- National Aeronautics and Space Administration
Citations
1,641
FWCI
27.20
field-weighted impact
References
42
Percentile
100%
vs. same field & year
Citations per year
Cited by
Q-learning
Machine Learning · 1992 · 8,916 citations
Technical Note: Q-Learning
Machine Learning · 1992 · 3,640 citations
Imitation Learning
ACM Computing Surveys · 2017 · 979 citations
References
A Learning Algorithm for Continually Running Fully Recurrent Neural Networks
Neural Computation · 1989 · 4,409 citations
Dynamic Programming and Markov Processes.
Journal of the American Statistical Association · 1961 · 3,447 citations
Learning to Predict by the Methods of Temporal Differences
Machine Learning · 1988 · 3,908 citations
Citation Network
How this paper connects to the literature. Drag to explore, click any node to open that paper.