Published in

DataSeries

Jesus Rodriguez

Jan 4

6 min read

DeepMind and OpenAI Ideas to Incorporate Human Feedback in Reinforcement Learning Agents

A paper from two years ago introduces some clever ideas to fine tune reward functions in reinforcement learning agents.

Source: https://medium.com/syncedreview/google-openai-deepmind-shared-task-behaviour-priors-can-boost-rl-and-generalization-d94f4d37077e

I recently started an AI-focused educational newsletter, that already has over 100,000 subscribers. TheSequence is a…

About Help Terms Privacy

Get the Medium app

Jesus Rodriguez

Jesus Rodriguez

CEO of IntoTheBlock, Chief Scientist at Invector Labs, I write The Sequence Newsletter, Guest lecturer at Columbia University, Angel Investor, Author, Speaker.

More from Medium

Jesus Rodriguez
in
Towards AI

OpenAI’s GPT-3 Inspired Model can Solve Problems from the Math Olympiads

Synced
in
SyncedReview

IBM’s Quantum-Enhanced Markov Chain Monte Carlo Algorithm Facilitates Complicated Probability…

Sharad Joshi
in
Geek Culture

Cutting through the hype around reasoning ability of large language models

Numenta

How do I Pursue a Career in Brain-Based AI?

Help
Status
Writers
Blog
Careers
Privacy
Terms
About
Knowable