logo
episode-header-image
Mar 2021
37m 11s

Goodhart's Law in Reinforcement Learning

Kyle Polich
About this episode
tail spinning
Up next
Jul 27
Social Choice for Fair Recommendations
Recommender systems influence nearly every aspect of our digital lives—but what does it mean for those systems to be fair? Robin Burke joins Data Skeptic to discuss the history of recommender systems, the limitations of optimizing purely for accuracy, and how ideas from social ch ... Show More
42m 56s
Jul 2
News Recommendations
News recommendation algorithms influence far more than what stories we click—they can shape our understanding of the world. In this episode, Kyle Polich speaks with Andreea Iana about responsible AI, filter bubbles, multilingual news recommendation, and her open-source NewsRecLib ... Show More
46m 6s
Jun 23
Give Users the Wheel
What if you could simply tell a recommendation system what you want instead of relying on likes, dislikes, and watch history? Kyle Polich talks with Fuyuan Lyu about the DPR framework, which combines large language models and traditional recommender systems to give users direct c ... Show More
35m 28s
Recommended Episodes
Apr 2025
Teaching LLMs to Self-Reflect with Reinforcement Learning with Maohao Shen - #726
Today, we're joined by Maohao Shen, PhD student at MIT to discuss his paper, “Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search.” We dig into how Satori leverages reinforcement learning to improve language model reasoning ... Show More
51m 45s
Oct 2021
Kevin Zatloukal — Machine Learning And Its Applications (EP.68)
tail spinning
51m 44s
Aug 2022
🧠 Scientific Machine Learning, FEM + ML, PINNs – Ehsan Haghighat | Podcast #79
Dr. Ehsan Haghighat is a Postdoctoral Fellow at UBC studying stochastic modeling and uncertainty quantification of engineering systems. Previously, he was a Postdoctoral Associate at MIT where he studied the assessment of induced seismicity due to CO2 sequestration and oil and ga ... Show More
57m 48s
Aug 2021
Applications of Variational Autoencoders and Bayesian Optimization with José Miguel Hernández Lobato - #510
Today we’re joined by José Miguel Hernández-Lobato, a university lecturer in machine learning at the University of Cambridge. In our conversation with Miguel, we explore his work at the intersection of Bayesian learning and deep learning. We discuss how he’s been applying this to ... Show More
42m 27s
Dec 2021
Samuel Cohen - Facebook AI Research & PhD at UCL #5
Our guest today is Samuel Cohen, PhD student at University College London (UCL) and visiting research scientist at Facebook AI Research (FAIR). In our conversation, we first dive into Samuel's first experience in AI, an internship at Check Point Software Technology where he devel ... Show More
46m 37s
Mar 2020
345: Machine Learning At Twitter
I speak with Dan Shiebler who works as a machine learning engineer at Twitter Cortex and at the same time, is doing a Ph.D. on applying category theory in machine learning. We discuss his work at Twitter, the importance of academics, and the future of machine learning. In this e ... Show More
1h 12m
Apr 2015
Starting Simple and Machine Learning in Meds
In episode nine we talk with George Dahl, of  the University of Toronto, about his work on the Merck molecular activity challenge on kaggle and speech recognition. George recently successfully defended his thesis at the end of March 2015. (Congrats George!) We learn about how net ... Show More
38m 24s
Feb 2011
Honey - The Golden Treasure
Dr Adam Hart explores the remarkable properties of honey, from its basic chemistry to the biological processes that create it. 
26m 31s
Feb 2018
MLG 029 Reinforcement Learning Intro
tail spinning
43m 21s
Jan 2020
PaccMann^RL: Designing Anticancer Drugs with Reinforcement Learning w/ Jannis Born - #341
Today we’re joined by Jannis Born, Ph.D. student at ETH & IBM Research Zurich, to discuss his “PaccMann^RL” research. Jannis details how his background in computational neuroscience applies to this research, how RL fits into the goal of anticancer drug discovery, the effect DL ha ... Show More
42m 4s