Skip to content
#030 Multi-Armed Bandits and Pure-Exploration (Wouter M. Koolen) episode artwork

Nov 20, 2020 1 hr 48 min

#030 Multi-Armed Bandits and Pure-Exploration (Wouter M. Koolen)

from Machine Learning Street Talk (MLST)

This week Dr. Tim Scarfe, Dr. Keith Duggar and Yannic Kilcher discuss multi-arm bandits and pure exploration with Dr. Wouter M. Koolen, Senior Researcher, Machine Learning group, Centrum Wiskunde & Informatica. Wouter specialises in machine learning theory, game theory, information theory, statistics and optimisation. Wouter is currently interested in pure exploration in multi-armed bandit models, game tree search, and accelerated learning in sequential decision problems. His research has been cited 1000 times, and he has been published in NeurIPS, the number 1 ML conference 14 times as well as lots of other exciting publications. Today we are going to talk about two of the most studied settings in control, decision theory, and learning in unknown environment which are the multi-armed bandit (MAB) and reinforcement learning (RL) approaches - when can an agent stop learning and start exploiting using the knowledge it obtained - which strategy leads to minimal learning time 00:00:00 What are multi-arm bandits/show trailer 00:12:55 Show introduction 00:15:50 Bandits 00:18:58 Taxonomy of decision framework approaches 00:25:46 Exploration vs Exploitation 00:31:43 the sharp divide between modes 00:34:12 bandit measures of success 00:36:44 connections to reinforcement learning 00:44:00 when to apply pure exploration in games 00:45:54 bandit lower bounds, a pure exploration renaissance 00:50:21 pure exploration compiler dreams 00:51:56 what would the PX-compiler DSL look like 00:57:13 the long arms of the bandit 01:00:21 causal models behind the curtain of arms 01:02:43 adversarial bandits, arms trying to beat you 01:05:12 bandits as an optimization problem 01:11:39 asymptotic optimality vs practical performance 01:15:38 pitfalls hiding under asymptotic cover 01:18:50 adding features to bandits 01:27:24 moderate confidence regimes 01:30:33 algorithms choice is highly sensitive to bounds 01:46:09 Post script: Keith interesting piece on n quantum http://wouterkoolen.info https://www.cwi.nl/research-groups/ma... #machinelearning

Episode details come from the podcast's RSS feed.

Embed this episode

Ready to play

#030 Multi-Armed Bandits and Pure-Exploration (Wouter M. Koolen)

0:00 1:48:08

No transcript yet.

Requests help us decide what to transcribe next.

Frequently asked questions

How long is this episode of Machine Learning Street Talk (MLST)?

This episode is 1 hour and 48 minutes long.

When was this Machine Learning Street Talk (MLST) episode published?

This episode was published on November 20, 2020.

Can I download this Machine Learning Street Talk (MLST) episode?

Yes. Use the download control on the episode player to save the publisher-provided media file.