CS422: Interactive and Embodied Learning

Winter 2022

Instructors: Nick Haber & Fei-Fei Li

Meeting times: Mo, We 1:30 - 3p

Location: CERAS 513

Note: first two weeks all-online, zoom details provided on Canvas.

Image of AI agents learning interactively

Course Description

Most successful machine learning algorithms of today use either carefully curated, human-labeled datasets, or large amounts of experience aimed at achieving well-defined goals within specific environments. In contrast, people learn through their agency: they interact with their environments, exploring and building complex mental models of their world so as to be able to flexibly adapt to a wide variety of tasks. One crucial next direction in artificial intelligence is to create artificial agents that learn in this flexible and robust way. Class will be a seminar, with discussion. Students will read and take turns presenting current works, and they will produce a proposal of a feasible next research direction. Topics build upon reinforcement learning techniques and include intrinsic motivation, model-based RL, self-supervised representation learning, multi-agent RL, human-AI interaction, and emergent communication.

The primary goal of this course is to provide a survey of techniques related to agents learning rich models of their world through interaction. Readings and discussions are planned with an eye towards germinating new work, and the project component should serve as a way to get started. The course is suitable for students looking to dive into recent works (from e.g. NeurIPS, ICML, and ICLR). Students should walk away from the course understanding not only relevant state-of-the-art approaches, but also its limitations, gaps in our understanding, benchmarks waiting to be created, and useful methods waiting to be fruitfully combined. This is an exciting, rapidly-growing field with many opportunities to quickly get started!

As a seminar in which we continually update readings, this course is intended to be suitable for repeated enrollment. See the 2021 offering here.

Prerequisites

Willing to read current AI literature (from e.g. NeurIPS, ICML, ICLR)
If not experienced in this, at least at a point where you're willing to learn this skill.
Proficiency in Python, and ideally Tensorflow or PyTorch
No assignments require this, but you will get a great deal more out of the course (and potentially make more compelling presentations and project) if you can e.g. look over a paper's github repo and play.
Knowledge in linear algebra, calculus, and statistics (MATH 19, 41, or 51, CS 109, or equivalent)
Again, no assignments require this, but you will get a great deal more out of readings if you are comfortable with these concepts.
CS 229, 231N, 234, or equivalent
Deep reinforcement learning will play a key role.

Class time

Winter quarter, 2022
Mo, We 1:30-3p

Office hours

By appointment
nhaber@stanford.edu

Forum, Zoom link, project submissions

Visit our Canvas page.

Readings

Coming soon. See last year's page,
but we will avoid repetition.

Grading

Project 40%
Presentations 30%
Discussion participation 30%

Resources

Hints/expectations for giving presentations.
Project timeline.
Have a look at some helpful resources
for relevant blog posts,
environments, and codebases.
This will grow throughout the quarter
as we find new ones!

Student responsibilities

Students will read required papers for each class, and students/groups of students (depending on enrollment) will take turns presenting. Note: each class has a required paper as well as a number of supplementary papers. The supplementary lists can get quite long -- this is not meant to be imposing! We simply think that each represents a handy constellation of papers for those interested in getting more acquainted with each subarea. We will try to provide a roadmap as we go, and feel free to ask for more context!

Students will produce a 6 page research proposal exploring a feasible next direction in depth, or some working demonstration of an idea. These will be “peer reviewed” by fellow students. For details, see our project timeline.

Schedule and readings

Papers subject to change! We are very open to alternative suggestions.

Supplementary reading forthcoming. To get an idea, please see last year's readings. We will avoid repetition of required papers and add several new ones, and this year will feature 1-2 guest speakers.

Framing and basic computational considerations

Conceptual framing, early attempts: world models, intrinsic motivation, behavior and performance metrics

Class 1: Framing and basic computational considerations.
Class 2: Intrinsic Motivation Systems for Autonomous Mental Development

Learning about embodiment and environment through interaction

Model-based reinforcement learning, skill learning, exploration, and their combination.

Class 3: Large-Scale Study of Curiosity-Driven Learning
Class 4: Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
Class 5: Initial project pitch
Class 6: Context on curiosity, model-based RL, skills.
Class 7: The Value Equivalence Principle for Model-Based Reinforcement Learning Alternatives: SimPLe, Goal GAN
Class 8: Diversity is All You Need: Learning Skills without a Reward Function

Learning about other agents through interaction

Self-supervised prediction of other agents, theory of mind, multi-agent RL methods in cooperative and competitive scenarios, emergent communication, human-AI interaction.

Class 9: Introductory lecture.
Class 10: On the interaction between supervision and self-play in emergent communication
Class 11: Learning with Opponent-Learning Awareness
Class 12: Guest speakers: Minae Kwon and Andy Shih
Class 13: End-of-unit-discussion. Supplementary: Active World Model Learning with Progress Curiosity

Future of benchmarking

Wrap-up

Class 16: Wrap-up discussion
Class 17: Project poster session (may extend into finals period if we need time)
Class 18: Guest speaker: Danijar Hafner