Programming Throwdown

180: Reinforcement Learning


Listen Later

Intro topic: Grills

News/Links:

  • You can’t call yourself a senior until you’ve worked on a legacy project
    • https://www.infobip.com/developers/blog/seniors-working-on-a-legacy-project
  • Recraft might be the most powerful AI image platform I’ve ever used — here’s why
    • https://www.tomsguide.com/ai/ai-image-video/recraft-might-be-the-most-powerful-ai-image-platform-ive-ever-used-heres-why
  • NASA has a list of 10 rules for software development
    • https://www.cs.otago.ac.nz/cosc345/resources/nasa-10-rules.htm
  • AMD Radeon RX 9070 XT performance estimates leaked: 42% to 66% faster than Radeon RX 7900 GRE
    • https://www.tomshardware.com/tech-industry/amd-estimates-of-radeon-rx-9070-xt-performance-leaked-42-percent-66-percent-faster-than-radeon-rx-7900-gre 

Book of the Show

  • Patrick: 
    • The Player of Games (Ian M Banks)
      • https://a.co/d/1ZpUhGl (non-affiliate)
  • Jason: 
    • Basic Roleplaying Universal Game Engine
      • https://amzn.to/3ES4p5i


Patreon Plug https://www.patreon.com/programmingthrowdown?ty=h


Tool of the Show

  • Patrick: 
    • Pokemon Sword and Shield
  • Jason: 
    • Features and Labels ( https://fal.ai )

Topic: Reinforcement Learning

  • Three types of AI
    • Supervised Learning
    • Unsupervised Learning
    • Reinforcement Learning
  • Online vs Offline RL
  • Optimization algorithms
    • Value optimization
      • SARSA
      • Q-Learning
    • Policy optimization
      • Policy Gradients
      • Actor-Critic
      • Proximal Policy Optimization
  • Value vs Policy Optimization
    • Value optimization is more intuitive (Value loss)
    • Policy optimization is less intuitive at first (policy gradients)
    • Converting values to policies in deep learning is difficult
  • Imitation Learning
    • Supervised policy learning
    • Often used to bootstrap reinforcement learning
  • Policy Evaluation
    • Propensity scoring versus model-based
  • Challenges to training RL model
    • Two optimization loops
      • Collecting feedback vs updating the model
    • Difficult optimization target
      • Policy evaluation
  • RLHF &  GRPO

★ Support this podcast on Patreon ★
...more
View all episodesView all episodes
Download on the App Store

Programming ThrowdownBy Patrick Wheeler and Jason Gauci

  • 4.5
  • 4.5
  • 4.5
  • 4.5
  • 4.5

4.5

550 ratings


More shows like Programming Throwdown

View all
Hanselminutes with Scott Hanselman by Scott Hanselman

Hanselminutes with Scott Hanselman

377 Listeners

Software Engineering Radio - the podcast for professional software developers by se-radio@computer.org

Software Engineering Radio - the podcast for professional software developers

272 Listeners

.NET Rocks! by Carl Franklin and Richard Campbell

.NET Rocks!

244 Listeners

The Changelog: Software Development, Open Source by Changelog Media

The Changelog: Software Development, Open Source

283 Listeners

Talk Python To Me by Michael Kennedy

Talk Python To Me

593 Listeners

Software Engineering Daily by Software Engineering Daily

Software Engineering Daily

624 Listeners

Soft Skills Engineering by Jamison Dance and Dave Smith

Soft Skills Engineering

269 Listeners

Super Data Science: ML & AI Podcast with Jon Krohn by Jon Krohn

Super Data Science: ML & AI Podcast with Jon Krohn

298 Listeners

Python Bytes by Michael Kennedy and Brian Okken

Python Bytes

213 Listeners

Data Engineering Podcast by Tobias Macey

Data Engineering Podcast

142 Listeners

Syntax - Tasty Web Development Treats by Wes Bos & Scott Tolinski - Full Stack JavaScript Web Developers

Syntax - Tasty Web Development Treats

982 Listeners

CoRecursive: Coding Stories by Adam Gordon Bell - Software Developer

CoRecursive: Coding Stories

189 Listeners

Practical AI by Practical AI LLC

Practical AI

189 Listeners

The Stack Overflow Podcast by The Stack Overflow Podcast

The Stack Overflow Podcast

63 Listeners

The Real Python Podcast by Real Python

The Real Python Podcast

140 Listeners