Credits: 3 (3-0-0)
Prerequisites: Any one of ELL409 / ELL784 / AIL701 / AIL721/ COL341 / COL774
Overlaps with: ELL729 approx. 50 %. [COL333, COL341, COL770, COL774, ELL409, ELL784, ELL802, ELL888) < 10%
Description
Introduction and Basics of RL, Markov Decision Processes (MDPs), Dynamic Programming, Monte Carlo Methods (Prediction), Temporal difference Methods (Prediction), Monte Carlo, TD Method (Control), Monte Carlo, TD Method (Control - cont.), N-step TD, EligibiJity Traces, Model based RL, (Action-)Value Function Approximation, Value Function Approximation, Policy Gradient, Policy Gradient, Misc. Topics.
Prerequisite Tree
flowchart TD
AIL722-1242[AIL722]
AIL722-1242 --- Or1243[Any one of]:::empty
ELL409-1244 --> COL106-1244[COL106]
Or1243 -.-> ELL409-1244[ELL409]
COL106-1244 --> COL100-1244[COL100]
ELL409-1244 --> MTL106-1244[MTL106]
Or1243 -.-> ELL784-1245[ELL784]
ELL784-1245 --> MTL106-1245[MTL106]
Or1243 -.-> AIL701-1246[AIL701]
AIL721-1247 --- Or1248[Any one of]:::empty
ELL409-1249 --> MTL106-1249[MTL106]
COL106-1249 --> COL100-1249[COL100]
ELL409-1249 --> COL106-1249[COL106]
Or1248 -.-> ELL409-1249[ELL409]
ELL784-1250 --> MTL106-1250[MTL106]
Or1248 -.-> ELL784-1250[ELL784]
Or1248 -.-> AIL701-1251[AIL701]
Or1248 -.-> COL774-1252[COL774]
COL774-1252 --> MTL106-1252[MTL106]
COL341-1253 --> MTL106-1253[MTL106]
Or1248 -.-> COL341-1253[COL341]
COL106-1253 --> COL100-1253[COL100]
COL341-1253 --> COL106-1253[COL106]
Or1243 -.-> AIL721-1247[AIL721]
Or1243 -.-> COL341-1254[COL341]
COL341-1254 --> COL106-1254[COL106]
COL341-1254 --> MTL106-1254[MTL106]
COL106-1254 --> COL100-1254[COL100]
COL774-1255 --> MTL106-1255[MTL106]
Or1243 -.-> COL774-1255[COL774]
classDef empty height:17px, fill:transparent, stroke:transparent;
classDef trueEmpty height:0px, width:0px;