Chapter
Reinforcement learning and temporal difference learning
55:34 - 1:02:43 (07:08)
This podcast episode features a discussion on reinforcement learning and temporal difference learning with a focus on the impact of Jerry Tesaro in developing these fields. The episode also touches upon the role of game playing and the use of neural nets in the learning process.
Clips
The podcast discusses the impact of temporal difference learning and reinforcement learning for solving complex problems in the field of computer science while highlighting the excitement they produce in the community.
55:34 - 58:32 (02:57)
Summary
The podcast discusses the impact of temporal difference learning and reinforcement learning for solving complex problems in the field of computer science while highlighting the excitement they produce in the community.
ChapterReinforcement learning and temporal difference learning
Episode#144 – Michael Littman: Reinforcement Learning and the Future of AI
PodcastLex Fridman Podcast
A back proppy network for playing backgammon trained on expert moves, created by a master student, ended up being impractical due to the inconsistency of neural nets and the importance of expert knowledge in the process of machine learning.
58:32 - 1:00:41 (02:09)
Summary
A back proppy network for playing backgammon trained on expert moves, created by a master student, ended up being impractical due to the inconsistency of neural nets and the importance of expert knowledge in the process of machine learning.
ChapterReinforcement learning and temporal difference learning
Episode#144 – Michael Littman: Reinforcement Learning and the Future of AI
PodcastLex Fridman Podcast
In the midst of discussions about the power of technology, it's important to remember the role that skilled individuals play.
1:00:41 - 1:01:45 (01:03)
Summary
In the midst of discussions about the power of technology, it's important to remember the role that skilled individuals play. Computers are powerful, but they can't achieve great things without the help of talented individuals, like hackers.
ChapterReinforcement learning and temporal difference learning
Episode#144 – Michael Littman: Reinforcement Learning and the Future of AI
PodcastLex Fridman Podcast
The host discusses the benefits of Emacs key bindings and using a Kinesis Keyboard, and how having a certain tool ingrained in your thought process can be difficult to replace or change.
1:01:45 - 1:02:43 (00:57)
Summary
The host discusses the benefits of Emacs key bindings and using a Kinesis Keyboard, and how having a certain tool ingrained in your thought process can be difficult to replace or change.