Developing the Foundations of Reinforcment Learning
2024 Turing laureates Andrew G. Barto and Richard S. Sutton discuss the theoretical background and practical application of reinforcement learning.
Sutton and Barto developed reinforcement learning, a machine learning method that trains neural networks by offering them rewards in the form of numerical values.
Most IT professionals worry their jobs will be replaced by AI tools, while more companies attribute reductions to “technology updates” rather than AI.
‘What I Think about When I Type about Talking’: Reflections on Text-Entry Acceleration Interfaces
The GenieTalk system was designed to address physical and cognitive barriers in sentence prediction and phrase retrieval systems.
What We're Reading
Opinion
Views on issues of broad interest to the computing community
BLOG@CACM
Thought leaders discuss relevant computing topics
Explore the latest issue
Table of Contents
Video
Multisensory Experiences: Formation, Realization, and Responsibilities
Sensory manipulation, privacy, and other ethical considerations must be carefully addressed as technology-enabled multisensory experiences evolve.
The Importance of Distrust in Trusting Digital Worker Chatbots
While trust is essential to promote human interaction with AI-powered digital workers, distrust may also play a role.
Prevalence and Prevention of Large Language Model Use in Crowd Work
LLMs may be particularly harmful in crowd work when the goal is to capture the diversity of human preferences, behaviors, or opinions.
Developing the Foundations of Reinforcment Learning
2024 Turing laureates Andrew G. Barto and Richard S. Sutton discuss the theoretical background and practical application of reinforcement learning.
Shape the Future of Computing
ACM encourages its members to take a direct hand in shaping the future of the association. There are more ways than ever to get involved.
Get InvolvedCommunications of the ACM (CACM) is now a fully Open Access publication.
By opening CACM to the world, we hope to increase engagement among the broader computer science community and encourage non-members to discover the rich resources ACM has to offer.
Learn More