Andrew G. Barto

United States Nuclear Regulatory Commission — United States

Computer Science · Physical Sciences

73h-index32.4kcitations234works0.02yr avg
OpenAlex↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Reinforcement Learning in Robotics(114), Evolutionary Algorithms and Applications(51), Neural Networks and Applications(26), Neural dynamics and brain function(25), Robot Manipulation and Learning(22)

Publications234 total

Rediscovering Reinforcement Learning
Communications of the ACM·2025
Participation in and Assessment of the Second DNCSH Public Workshop
2025Open Access
Adaptive Real-Time Dynamic Programming
2023
TD-DeltaPi: A Model-Free Algorithm for Efficient Exploration
Proceedings of the AAAI Conference on Artificial Intelligence·2021· 1 citedOpen Access
Adaptive Step-Size for Online Temporal Difference Learning
Proceedings of the AAAI Conference on Artificial Intelligence·2021· 40 citedOpen Access
Looking Back on the Actor–Critic Architecture
IEEE Transactions on Systems Man and Cybernetics Systems·2020· 41 citedOpen Access
Optimal Control Methods for Simulating the Perception of Causality in Young Infants
Psychology Press eBooks·2020· 18 cited
Editorial: Intrinsically Motivated Open-Ended Learning in Autonomous Robots
Frontiers in Neurorobotics·2020· 23 citedOpen Access
Preventing undesirable behavior of intelligent machines
Science·2019· 144 citedOpen Access
Reinforcement learning with analogue memristor arrays
Nature Electronics·2019· 363 cited
Reinforcement Learning: Connections, Surprises, Challenges
AI Magazine·2019· 11 citedOpen Access
Some Learning Tasks from a Control Perspective
2018· 8 cited
Enriching behavioral ecology with reinforcement learning methods
Behavioural Processes·2018· 64 citedOpen Access
On Ensuring that Intelligent Machines Are Well-Behaved
arXiv (Cornell University)·2017· 10 citedOpen Access
Adaptive Real-Time Dynamic Programming
Encyclopedia of Machine Learning and Data Mining·2017
Reinforcement learning, efficient coding, and the statistics of natural tasks
Current Opinion in Behavioral Sciences·2015· 57 cited
Online Bayesian changepoint detection for articulated motion models
2015· 45 cited
Review of Fissile Material Exemptions and General Licenses in 10 CFR Part 71
OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)·2015Open Access
Intrinsic motivations and open-ended development in animals, humans, and robots
Frontiers Media SA eBooks·2015· 1 cited
Learning grounded finite-state representations from unstructured demonstrations
The International Journal of Robotics Research·2014· 192 cited
page 1 of 12Next →

Frequent Co-authors

Richard S. Sutton(8), James C. Houk(6), George Konidaris(5), Satinder Singh(4), Steven J. Bradtke(3), Sridhar Mahadevan(3), Nuttapong Chentanez(2), Robert H. Crites(2), Özgür Şimşek(2), Jay Buckingham(2), Alec Solway(2), Carlos Diuk(2), Yael Niv(2), Matthew Botvinick(2), Scott Niekum(2), Sarah Osentoski(2), N. Sitkoff(2), Jennie Si(1), Warren B. Powell(1), Don Wunsch(1)