Ruprecht-Karls-Universität Heidelberg
Bilder vom Neuenheimer Feld, Heidelberg und der Universität Heidelberg
Siegel der Uni Heidelberg

Imitation Learning - Materialübersicht

« zurück

Tentative lecture plan

DateLecturesComment
17.02.2020Course Introduction
Potential Presentations/Projects
Behavioral Cloning		Basics intro

Videos:
ALVINN
Super Tux
Mario
Speech Synthesis
18.02.2020Introduction to Online Learning
Structured Prediction
Learning to search for structured prediction		Basics
19.02.2020Aggregation Methods
Intro to Reinforcement Learning
Inverse Reinforcement Learning		Basics
20.02.2020Presentation topics:
AggreVaTe -- Maksim Schreck, slides, paper
AggreVaTed -- reading group, annotated paper, paper
LOLS -- Fabian Strobel, slides, paper
LOKI -- paper
GANs and GAIL -- reading group, annotated Finn et al., annotated Ho & Ermon, paper		Student presentations
21.02.2020Project topics and related papers:
  1. IRL with MaxEnt -- Jan Stanicki, Julius Unverfehrt (paper, paper)
  2. MT Oracle/IRL with MaxMargin Planning -- Raphael Baumgartner, Luca Hormann (paper, paper, paper, paper)
  3. Deep Q-learning -- Rene Bucchia, Antonio Ruiz, Carlos Rios (paper)
  4. Knowledge Distillation with Dagger -- Vanessa Zuber, Nathaniel Berger (paper, paper)
Student presentations
zum Seitenanfang