2024 ACM A.M. Turing Award: Richard S Sutton and Andrew G. Barto for Reinforcement Learning

Matjaz Gams

Abstract


The 2024 ACM A.M. Turing Award (the “Nobel Prize of Computing”) was awarded to Andrew G. Barto and Richard S. Sutton “for developing the conceptual and algorithmic foundations of reinforcement learning.” Announced on 5 March 2025, the honor not only celebrates nearly five decades of pioneering scholarship but also signals that reinforcement learning (RL) has moved from the periphery of artificial-intelligence research to its very center —most visibly through its role in training large-language models (LLMs).

Full Text:

PDF

References


References

R. S. Sutton and A. G. Barto, Reinforcement Learning: An Introduction, 2nd ed., MIT Press, Cambridge, MA, 2018.

D. Silver et al., “Mastering the Game of Go with Deep Neural Networks and Tree Search,” Nature, vol. 529, pp. 484–489, 2016.

L. Ouyang et al., “Training Language Models to Follow Instructions with Human Feedback,” Advances in Neural Information Processing Systems 35, 2022.

N. Savage, “A Rewarding Line of Work,” Communications of the ACM, vol. 68, no. 6, pp. 8–10, 2025, DOI: 10.1145/3727966.

L. Hoffmann, “Developing the Foundations of Reinforcement Learning,” Communications of the ACM, vol. 68, no. 6, p. 96, 2025, DOI: 10.1145/3724079.

D. Silver et al., “A General Reinforcement Learning Algorithm that Masters Chess, Shogi, and Go through Self Play,” Science, vol. 362, no. 6419, pp. 1140–1144, 2018.

V. Mnih et al., “Human Level Control through Deep Reinforcement Learning,” Nature, vol. 518, pp. 529–533, 2015.

C. Evans and D. Gao, “DeepMind AI Reduces Google Data Centre Cooling Costs,” DeepMind Blog, 2018.

A. Mirhoseini et al., “A Graph Placement Methodology for Fast Chip Design,” Nature, vol. 594, pp. 207–212, 2021.




DOI: https://doi.org/10.31449/inf.v49i3.9999

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.