
180: Reinforcement Learning
From Programming Throwdown by Patrick Wheeler and Jason Gauci
March 17, 2025 · 1h 52m · Episode 180
About this episode
Patrick and Jason introduce reinforcement learning and discuss its challenges alongside other learning paradigms.
Patrick and Jason introduce reinforcement learning and place it alongside supervised and unsupervised learning. They cover Q-learning, SARSA, policy gradients, actor-critic methods, PPO, imitation learning, and why training and evaluating RL systems is so challenging.
People in this episode
Hosts: Patrick Wheeler, Jason Gauci
Topics covered
- reinforcement learning
- supervised learning
- unsupervised learning
- Q-learning
- SARSA
- policy gradients
- training challenges
Keywords
- reinforcement learning
- Q-learning
- SARSA
- policy gradients
- actor-critic methods
- PPO
- imitation learning
- training
- evaluation
Mentioned in this episode
Books & works: Reinforcement Learning, Q-learning, SARSA, policy gradients, actor-critic methods, PPO, imitation learning
More episodes of Programming Throwdown
- 187: Agentic Coding · May 2, 2026 · 1h 38m
- 186: Becoming a Manager · February 3, 2026 · 1h 28m
- 185: Workflow Orchestrators · November 4, 2025 · 1h 32m
- 184: Asynchronous Programming · September 23, 2025 · 1h 31m
- 183: Landing a Software Job in 2025 · July 31, 2025 · 1h 47m
- 182: AI Assisted Coding · June 30, 2025 · 1h 38m
Explore listener stats, chart rankings, contacts and more on the Programming Throwdown podcast page.