Foundations of Autonomous Decision Making under Uncertainty
10-734, Fall 2024
|
|
|
|
|
Note: this is a tentative lecture schedule that is subject to change.
Date |
Topic |
Notes |
Useful links |
|
|
|
|
Aug 27 Tuesday |
Intro to Decision Making |
Lecture1.pdf |
|
Aug 29 Thursday |
Experimental Design |
Lecture2.pdf |
On Computationally Tractable Selection of Experiments Near optimal Design of experiments via Regret Minimization
Combinatorial Algorithms for Optimal Design |
Sept 3 Tuesday |
Active Learning |
Lecture3.pdf |
Active Learning Survey-Burr Settles Noise-adaptive margin based active learning linear classifiers Active Learning Decision Trees1,2 Active Learning NN: Coresets |
Sept 5 Thursday |
Multi Armed Bandits |
Lecture4.pdf |
Intro to Multi-Armed Bandits, Ch1 |
Sept 10 Tuesday |
UCB Sampling |
Lecture5.pdf |
Intro to Multi-Armed Bandits, Ch1,2 |
Sept 12 Thursday |
Nonparametric Bandits |
Lecture6.pdf |
Intro to Multi-Armed Bandits, Ch4 |
Sept 17 Tuesday |
Linear Bandits |
Lecture7.pdf |
Reinforcement Learning: Theory & Algorithms, Ch6, Dani et al, Abbasi et al |
Sept 19 Thursday |
Thompson Sampling |
Lecture8.pdf |
Intro to Multi-Armed Bandits, Ch3 Optimize via posterior sampling, Russo_VanRoy |
Sept 24 Tuesday |
GP bandits |
Lecture9.pdf |
GP optimization in Bandit Setting |
Sept 26 Thursday |
Model selection in Bandits |
Lecture10.pdf |
CORRAL,SmoothCORRAL,RBBE,ModCB, AdaptLipConstant,AdaptKernel |
Oct 1 Tuesday |
Online learning with experts |
Lecture11.pdf |
Intro to Multi-Armed Bandits, Ch5 |
Oct 3 Thursday |
Adversarial Bandits |
Lecture12.pdf |
Intro to Multi-Armed Bandits, Ch6 |
Oct 8 Tuesday |
Class canceled, TA office hours |
|
|
Oct 10 Thursday |
Contextual & Generalized Bandits |
|
Intro to Multi-Armed Bandits, Ch8, Square-CB paper |
Oct 15 Tuesday |
No Class - FALL BREAK |
Oct 17 Thursday |
No Class - FALL BREAK |
Oct 22 Tuesday |
RCT and Bandits |
Lecture14.pdf |
ATE estimation_Kato et al |
Oct 24 Thursday |
Reinforcement Learning |
Lecture15.pdf |
RL_theory book AJKS, Ch 1.1,1.2 |
Oct 29 Tuesday |
Value and Policy Iteration |
Lecture16.pdf |
RL_theory book AJKS, Ch 1.3 |
Oct 31 Thursday |
Tabular MDP |
Lecture17.pdf |
RL_theory book AJKS, Ch 7 |
Nov 5 Tuesday |
No Class - ELECTION DAY |
Nov 7 Thursday |
Linear MDP |
Lecture18.pdf |
LSVI-UCB paper |
Nov 12 Tuesday |
Linear MDP contd.. |
Lecture19.pdf |
LSVI-UCB paper |
Nov 14 Thursday |
Nonlinear RL |
Lecture20.pdf |
General_func_Akshaynotes |
Nov 19 Tuesday |
Offline & Hybrid RL |
|
OfflineRL_FQI, HybridRL |
|
Nov 21 Thursday |
Policy Gradient |
Lecture22.pdf |
RL_theory book AJKS, Ch 11 |
Nov 26 Tuesday |
Human-AI decision making |
Lecture23.pdf |
|
Nov 28 Thursday |
No Class - THANKSGIVING |
Dec 3 Tuesday |
Project Presentations |
|
|
Dec 5 Thursday |
Project Presentations |
|
|
|
|
|