Time and Place: Monday and Thursday 11:45 am - 1:25 pm, East Village 024
Khoury College of Computer Sciences
Instructor: Chris Amato
TAs listed on Canvas and Piazza
| Date | Topic | Notes | Reading | Assignment out/due |
|---|---|---|---|---|
| 9/10 | Introduction, Agents and Problem Domains | Course Introduction
|
Ch 1 -- 2 | Look at official Python Tutorial. |
| 9/14 | Uninformed Search | Search I |
Ch 3.1 -- 3.4 | |
| 9/17 | Informed Search | Search II |
Ch 3.5 --3.6, 4.1 | Programming assignment 1 (Search) out |
| 9/21 | Informed Search (cont.) and Adversarial Search | Competition in games | Ch 5.1 -- 5.3, 5.5 | |
| 9/24 | Adversarial Search (cont.) | Problem set 1 due | ||
| 9/28 | Uncertainty and Probability | Ch 12.1 -- 12.5 | |
|
| 10/1 | Graphical Models/Bayes Nets | Probabilistic modeling | Ch 13.1 -- 13.2 | PA1 due; Programming assignment 2 (Multi-Agent) out |
| 10/5 | Bayes Net Inference | Exact inference and sampling
|
Ch 13.3 -- 13.4
|
Problem set 2 due; Project description out |
| 10/8 | Markov Models | Sequential modeling |
Ch 14.1 -- 14.3 |
|
| 10/12 | No class (Indigenous Peoples Day) | |||
| 10/15 | Exam 1 | |||
| 10/19 | Markov Decision Processes (MDPs) | Incorporating actions |
Ch 17.1 -- 17.2 | Programming assignment 3 (Reinforcement Learning) out |
| 10/22 | Planning with MDPs | Ch 5.4 (MCTS), (optional: SB 3.1--3.3, 3.5--3.6, SB 4.1--4.4) | PA2 due | |
| 10/26 | Reinforcement Learning | Learning for MDPs |
Ch 22 | Project proposal due |
| 10/29 | Reinforcement Learning (cont.) | Function approximation and policy gradients | (optional: SB 6.5, SB 13.1--13.5) |
Problem set 3 due |
| 11/2 | Intro to Machine Learning | Supervised learning |
Ch 19.1 -- 19.2 | |
| 11/5 | More Supervised Learning | Ch 19.4 -- 19.7 |
PA3 due | |
| 11/9 | Deep Learning | Ch 21 |
||
| 11/12 | Deep Reinforcement Learning | DQN, actor-critic and PPO, robotics applications |
(optional: SB 9.1--9.4, 16.5) |
Problem set 4 due; Programming assignment 4 (Machine Learning) out |
| 11/16 |
Attention, Transformers and LLMs | From sequence models to language models |
Ch 24 (plus external notes) |
|
| 11/19 | Exam 2 | |||
| 11/23 | Alignment: RLHF, Reward Models and DPO | Preference-based post-training |
External readings |
|
| 11/26 | No class (Fall break) | |||
| 11/30 |
Advanced topics: Multi-Agent Reinforcement Learning | Dec-POMDPs and multi-agent coordination |
External readings |
Programming assignment 4 due |
| 12/3 | Project Presentations | |||
| 12/7 | Project Presentations | |||
| 12/10 | Project Presentations | |||
| 12/14 | Advanced Topics | |||
| 12/15 |
Project Reports Due | Report due at 11:59 PM -- This is a hard deadline, no extensions | ||
| 12/17 | Open Slot |
Important note: unless noted otherwise, all readings and assignments are due on the day that they appear in the schedule.
Unless noted otherwise, all readings are from Artificial Intelligence: A Modern Approach, 4th Ed., Russell and Norvig.