Science ❯ Computer Science ❯ Machine Learning

Reinforcement Learning

Model Optimization Model Training Large Language Models Open Source AI AI Research Model Evaluation Applications Generative Models AI Reasoning Models Explainable AI Learning from Human Feedback User Feedback Natural Language Processing Efficient AI Systems AI Training Methods Imitation Learning Autonomous Systems

UAE Releases K2 Think, an Open-Source 32B Reasoning Model

The team invites scrutiny by releasing full code and weights alongside claims of parity on math and science tests.

Leading AI Researchers Urge Chains-of-Thought Monitoring to Preserve Transparency

Andrew Barto and Richard Sutton Awarded Turing Prize for Reinforcement Learning Innovations