To teach an AI agent a new task, like how to open a kitchen cabinet, researchers often use reinforcement learning—a trial-and-error process where the agent is rewarded for taking actions that get it …
This is a companion discussion for the article “New method uses crowdsourced feedback to train robots - https://techxplore.com/news/2023-11-method-crowdsourced-feedback-robots.html” submitted on the community's news feed.
Reply to this topic to share your thoughts on this article.