Course Schedule

The schedule is tentative and may be adjusted as the semester progresses. Readings refer to Sutton and Barto, second edition. Course-specific materials will be posted through this site and Canvas.

No class Tutorial / Q&A Project milestone
Week Date Lecture Material Assignment
1Tue, Aug 18 Course introductionAgent–environment interaction, rewards, examples, and challenges S&B 1.1–1.4
1Thu, Aug 20 Multi-armed bandits IAction values, sample averages, constant step sizes, and ε-greedy S&B 2.1–2.5
2Tue, Aug 25 Multi-armed bandits IIOptimism, UCB, gradient bandits, nonstationarity, and regret S&B 2.5–2.8
2Thu, Aug 27 Markov decision processes IStates, actions, transition models, Markov property, and policies S&B 3.1–3.4
3Tue, Sep 1 Markov decision processes IIReturns, discounting, episodic and continuing tasks, and value functions S&B 3.3–3.7 Homework 1 + Coding Assignment 1 released
3Thu, Sep 3 Bellman equations and policy evaluation S&B 3.5–3.6, 4.1
4Tue, Sep 8 Policy improvement and policy iteration S&B 4.2–4.3
4Thu, Sep 10 Value iteration and DP S&B 4.4–4.7
5Tue, Sep 15 Monte Carlo prediction S&B 5.1–5.3
5Thu, Sep 17 Monte Carlo control and off-policy learning S&B 5.4–5.7
6Tue, Sep 22 Temporal-difference predictionTD(0), bootstrapping, and MC–TD comparison S&B 6.1–6.3
6Thu, Sep 24 TA-led coding tutorial: tabular TD controlImplement SARSA and Q-learning, run controlled experiments, and compare their learning behavior S&B 6.4–6.7 Homework 1 + Coding Assignment 1 DUE
7Tue, Sep 29 No class — IROS travelOptional guided review Homework 2 + Coding Assignment 2 released
7Thu, Oct 1 No class — IROS travel
8Tue, Oct 6No class — Fall Break
10Tue, Oct 8 Homework and coding assignment Q&A / review sessionTroubleshoot Homework and Coding Assignment 1-2, review common issues Bring your questions
9Tue, Oct 13 Combined project (building a complete RL system) — midterm milestoneProject integration Project specification Bring a laptop
9Thu, Oct 15 Combined project (building a complete RL system) — midterm milestoneSystem demonstrations, testing, feedback, and milestone review Project specificationBring a laptop
8Thu, Oct 20 n-step TD S&B 7.1–7.3; selected Ch. 12 Final project phase begins: train an RL agent in simulation
10Thu, Oct 22 Planning and learning IDyna, direct and indirect learning, and simulated experience S&B 8.1–8.3 Homework 2 + Coding Assignment 2 DUE
11Tue, Oct 27 Planning and learning IIPrioritized sweeping, trajectories, and planning at decision time S&B 8.4–8.11 Homework 3 + Coding Assignment 3 released
11Thu, Oct 29 Value function approximation ILinear features, objectives, and semi-gradient prediction S&B 9.1–9.5
12Tue, Nov 3No class — Election Day
12Thu, Nov 5 Value function approximation IIControl, off-policy instability, and the deadly triad S&B 10.1, 11.1
13Tue, Nov 10 Policy gradients IParameterized policies, score functions, and REINFORCE S&B 13.1–13.3 Final project progress check (submit a short summary report)
13Thu, Nov 12 Policy gradients IIBaselines, actor–critic, variance, and continuing tasks S&B 13.4–13.5
14Tue, Nov 17 Deep reinforcement learningDQN, experience replay, target networks, representation learning, and training stability
14Thu, Nov 19 Reward design and learning from preferencesReward hypothesis, reward shaping, inverse reinforcement learning, and preference-based feedback Homework 3 + Coding Assignment 3 DUE
15Tue, Nov 24 RL beyond the Markov propertyPartial observability, state representation, memory, belief states, and recurrent agents
15Thu, Nov 26No class — Thanksgiving Recess
16Tue, Dec 1 Final project poster and demo sessionsPresent the completed system, trained RL agent, experimental results, and lessons learned Poster and demonstration guidelines Project poster and live demo

UTK calendar notes: Full-session classes end Tuesday, December 1; Study Day is Wednesday, December 2; final exams run December 3–9. Final project deadlines will be confirmed in the class.