Schedule
Dates | Schedule | Topics covered | Due |
---|---|---|---|
Sep 14 | Intro to MDP | Intro to Prob | |
Sep 21 | Tabular RL - VI, PI | class work | Test quiz |
Sep 28 | Model-Free Policy Evaluation | class work | |
Oct 5 | Model-Free Control: Q-Functions, TD-Methods, SARSA | How to use remote UTM compute/colab | Quiz 1 |
Oct 12 | reading week - no class | no tutorial | no class |
Oct 19 | Value-based Methods : FVI | discuss A1 | Assmt 1 + Quiz 2 |
Oct 26 | Deep RL: Value based Methods and CNNs | Intro to project resources | Quiz 3 |
Nov 2 | Policy Search - Policy Gradients | Implementation of DQN | Assmt 2 + Project Proposals + Quiz 4 |
Nov 9 | Policy Search - cont. | Implementation of PG - TRPO, PPO | Quiz 5 |
Nov 16 | Model-based planning: Monte Carlo Tree Search, CEM | Evaluation of RL approaches | Assmt 3 + Quiz 6 |
Nov 23 | Model-based RL | Project Clinics | Quiz 7 |
Nov 30 | Model-based Policy Learning and Exploration | Project Clinics | Assmt 4 + Quiz 8 |
Dec 7 | Offline RL and Imitation Learning | In class presentations | Project report |
Dec 10 | Final Exam |