CSCI 2951X: Reintegrating AI
(Spring 2024)




Further Reading


The goal of AI has been to build complete intelligent agents, yet the field has been fragmented into a collection of problem-specific areas of study. We will first spend a few weeks in lecture covering a new approach to integrating existing AI subfields into a single agent architecture, and remainder of the semester on self-directed, semester-long research projects.

Grading will be based on a mid-semester project proposal, and a substantial open-ended final project. The projects will be multi-disciplinary in nature but students will have the opportunity to work in small groups, so they need not necessarily have expertise in the relevant areas. All students need special permission to enroll; advanced undergraduate students welcome.

The 2018 incarnation of this course was a reading seminar; the old website and reading lists are here.

George Konidaris
Office: CIT 447
Email: gdk at brown dot edu

[Back to top]


The first class is on Tuesday January 30th (there will be no class on January 25th), meeting weekly on Tuesday and Thursday from 1-2:20pm in CIT 477 (Lubrano). The first few sessions will be lectures, after which we will break into project groups, and weekly meetings will be progress check-ins and discussions with each group.

[Back to top]

b Project

Your project will be a substantial creative and original piece of work. I expect you to design and implement theory and experiments studying some algorithm or model that is aligned with the course content - i.e., a model that integrates at least two aspects of AI research in an interesting way.

I expect it to have approximately the length, form, and content of a conference paper at a good AI conference (though it need not be publishable). That means careful, clear, and precise writing, a well-formalized and thoughtfully evaluated point, and thorough referencing throughout. It does not necessarily have to be an original contribution, although that would be nice. If it is not, then I expect at least an original evaluation that is relevant to our topic (e.g., an existing algorithm is tried in a new domain or addresses a setting that speaks to what we have discussed).

The study will be graded on insight, completeness, and clarity. These studies can be completed in groups of ~5 people.

This year your project proposal will have to include a half-page statement explaining which model of a general intelligence you are using, and how your project fits into realizing that model.

The project accounts for 100% of your grade and is due at the end of the reading period (May 8th).

There is an intermediate deadline: a 2-page project proposal due by approximately mid-March, which identifies the topic, names the group, and sketches out what you hope to accomplish in the study. I will use these to discuss the project with each group to make sure they're on an appropriate path.

[Back to top]


General background for embodiment and general AI (all quite dated):


The data-driven approach:

More cognitive approaches:

MDPs and RL:

  • D. Silver, S. Singh, D. Precup, and R.S. Sutton. Reward is Enough. Artificial Intelligence 299, October 2021.
  • Kaelbling, Leslie Pack, Michael L. Littman, and Andrew W. Moore. Reinforcement learning: A survey. Journal of artificial intelligence research 4 (1996): 237-285.

Object-Oriented MDPs:

Abstraction in RL:

Problem-Specific Abstractions:


Natural Language for MDPs:

Further Reading

Readings from the following books are recommended for more in-depth engagement with the topic, though note that all of these are now dated:

Also worth reading, but much more about philosophy than CS, is:
  • Mind and Cognition, 2nd ed, W.G. Lycan, ed.

These books and readings will be of interest to students who want to understand the probabilistic foundation of AI more deeply:

  • Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference, by Judea Pearl.
  • Probability Theory: The Logic of Science, by E.T. Jaynes.
  • Probabilistic Logic, by Nils Nilsson. In Artificial Intelligence 28 (1986), 71-85.

[Back to top]