flâneur

CSE 291 - AI Agents - UCSD CSE

pearls-lab.github.io · 788 words · saved by 1 readers

This course will cover the basics of (1) what LLM-based AI Agents actually are; (2) where they can be useful (and where they are not); and (3) how to safely train and deploy an agent for a given virtual domain. Students should be familiar with basic CS concepts such as Search (A*, Monte Carlo Tree Search) and Deep Learning concepts such as Transformers (how self-attention works) and the basics of how Large Language Models are (pre-)trained. Students are expected to come into the class with the ability to implement these concepts from scratch (in Python/numpy) and also be able to use popular libraries such as Huggingface. Basic knowledge of Reinforcement Learning (what is a Markov Decision Process, differences between online and offline RL, RL from Human Feedback) is a plus but not required. Undergrad Intro to AI/RL, and grad level Intro to Deep Learning / NLP types of courses are highly recommended Office Hours (see the Staff page for office hour locations) There is no textbook for thi

CSE 291 - AI Agents - UCSD CSE Skip to main content A great example of what you could build if you take this class is the [AI Dungeon](https://play.aidungeon.io/), which is an interactive fiction game that was developed by a student at BYU using [Open AI's GPT-2](https://openai.com/blog/better-language-models/) large scale language model. --> First day of class is Thursday, January 13, 2022 at 1:45pm-3:15pm Eastern. It will take place virtually. Here is the [Zoom link](https://upenn.zoom.us/j/95868341588?pwd=a0NvbkhtUEdYTTk5d0Vmc2VvcHJrUT09). We look forward to seeing you there! --> Course num

saved by

related reading