RLHF: How to Learn from Human Feedback with Reinforcement Learning
Description:
Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Grab it
Explore the intricacies of Reinforcement Learning from Human Feedback (RLHF) in this 59-minute lecture delivered at the 2023 Cooperative AI Summer School. Delve into the innovative techniques for leveraging human input to enhance AI systems as presented by Natasha Jaques, a Senior Research Scientist at Google Brain. Learn about the applications of RLHF in multi-agent and human-AI interactions, drawing from Jaques' extensive research background and accolades in the field of Social Reinforcement Learning. Gain insights from her experiences at prestigious institutions like MIT, UC Berkeley, DeepMind, and OpenAI, and discover how RLHF is shaping the future of AI development and human-machine collaboration.
RLHF: How to Learn from Human Feedback with Reinforcement Learning