Stanford Seminar - Decision Transformer: Reinforcement Learning via Sequence Modeling
Stanford University via YouTube
-
21
-
- Write review
Free courses from frontend to fullstack and AI
Learn the Skills Netflix, Meta, and Capital One Actually Hire For
Overview
Google, IBM & Meta Certificates – 40% Off
One Coursera Plus subscription covers most Professional Certificates on Coursera.
Unlock All Certificates
This seminar introduces Decision Transformer, which frames reinforcement learning as conditional sequence modeling. It describes how a causally masked Transformer uses desired returns, past states, and actions to generate future actions, and reports results on Atari, OpenAI Gym, and Key-to-Door tasks.
Syllabus
CS25 I Stanford Seminar 2022 - Decision Transformer: Reinforcement Learning via Sequence Modeling
Taught by
Stanford Online
Tags
Reviews
4.5 rating, based on 2 Class Central reviews
Showing Class Central Sort
-
This online course has truly exceeded my expectations with its comprehensive content. The modules are well-structured, making it easy to follow along and grasp the concepts. I found the interactive exercises particularly helpful in reinforcing what I learned. Moreover, the instructor's clear explanations and engaging teaching style kept me motivated throughout. Overall, I highly recommend this course to anyone seeking to expand their knowledge on the subject.
-
It was great learning from him,the detailing and explanation was too good!! Great couse for Reinforcement Learning!