reinforcement learning – Page 3 – Andrew Fairless, Ph.D.

What I Read: AI, Human Values

By Andrew Fairless on February 22, 2023December 16, 2022

https://www.quantamagazine.org/what-does-it-mean-to-align-ai-with-human-values-20221213/ What Does It Mean to Align AI With Human Values?Melanie MitchellDecember 13, 2022 “Making sure our machines understand the intent behind our instructions is an important problem that requiresContinue readingWhat I Read: AI, Human Values

What I Read: Offline RL, Large Language Models

By Andrew Fairless on February 21, 2023December 16, 2022

https://sergeylevine.substack.com/p/offline-rl-and-large-language-models Offline RL and Large Language ModelsSergey LevineDec 4 “What if the purpose of a language model should not be to generate text at all, at least not directly? …Continue readingWhat I Read: Offline RL, Large Language Models

What I Read: Causal Confounds, Sequential Decision

By Andrew Fairless on February 6, 2023December 4, 2022

https://blog.ml.cmu.edu/2022/11/28/causal-confounds-in-sequential-decision-making/ Causal Confounds in Sequential Decision MakingGokul SwamyNovember 28, 2022 “Using techniques from causal inference, we derive provably correct and scalable algorithms for sequential decision making in these sorts ofContinue readingWhat I Read: Causal Confounds, Sequential Decision

What I Read: Matrix Multiplication

By Andrew Fairless on January 30, 2023December 4, 2022

https://www.quantamagazine.org/ai-reveals-new-possibilities-in-matrix-multiplication-20221123/ AI Reveals New Possibilities in Matrix MultiplicationBen BrubakerNovember 23, 2022 “Inspired by the results of a game-playing neural network, mathematicians have been making unexpected advances on an age-old mathContinue readingWhat I Read: Matrix Multiplication

What I Read: Learning to Imitate

By Andrew Fairless on January 17, 2023December 4, 2022

https://ai.stanford.edu/blog/learning-to-imitate/ Learning to ImitateDivyansh GargNovember 1, 2022 “A key aspect of human learning is imitation…. How can we enable our artificial agents to similarly acquire such fast learning ability?”

What I Read: The Farama Foundation

By Andrew Fairless on December 22, 2022November 5, 2022

https://farama.org/Announcing-The-Farama-Foundation Announcing The Farama FoundationThe future of open source reinforcement learning25 October 2022 “This means that the barrier to reinforcement learning seeing widespread deployment is a tooling problem…. Our grandContinue readingWhat I Read: The Farama Foundation

What I Read: Pre-Trained Models, Robotics

By Andrew Fairless on December 21, 2022November 5, 2022

https://sergeylevine.substack.com/p/general-purpose-pre-trained-models General-Purpose Pre-Trained Models in RoboticsCan we (pre-) train policies to control any robot for any task?Sergey LevineOct 16 “In robotics, learning policies from a small amount of data isContinue readingWhat I Read: Pre-Trained Models, Robotics

What I Read: undesired goals

By Andrew Fairless on December 20, 2022November 5, 2022

How undesired goals can arise with correct rewardsRohin Shah, Victoria Krakovna, Vikrant Varma, Zachary KentonOctober 7, 2022 “As we build increasingly advanced artificial intelligence (AI) systems, we want to makeContinue readingWhat I Read: undesired goals

What I Read: Against Naive AI Scaling

By Andrew Fairless on July 27, 2022June 27, 2022

https://jacobbuckman.com/2022-06-14-an-actually-good-argument-against-naive-ai-scaling/ An Actually-Good Argument Against Naive AI ScalingJacob BuckmanPosted on June 14, 2022 “…the debate is whether scaled-up language models in the style of GPT-3 will eventually become general intelligences,Continue readingWhat I Read: Against Naive AI Scaling

What I Read: What is Reinforcement Learning

By Andrew Fairless on July 20, 2022June 27, 2022

https://castlelab.princeton.edu/what-is-rl/ What is Reinforcement LearningWarren B PowellProfessor Emeritus, Princeton University “…I provide a brief introduction to modeling sequential decision problems… and then designing policies. As I watch the evolution ofContinue readingWhat I Read: What is Reinforcement Learning

Tag: reinforcement learning