Algorithms for Imitation Learning

@article{osa2018algorithmic,

  title={An algorithmic perspective on imitation learning},

  author={Osa, Takayuki and Pajarinen, Joni and Neumann, Gerhard and Bagnell, J Andrew and Abbeel, Pieter and Peters, Jan},

  journal={Foundations and Trends{\textregistered} in Robotics},

  volume={7},

  number={1-2},

  pages={1--179},

  year={2018},

  publisher={Now Publishers, Inc.}

}

  Paper Assignment

       (Student)     -> PaperID

       (Erdenezul)   -> 3

       (Cihan)       -> 12

       (Jan)         -> 6

       (Ralf)        -> 5

       (Katharina)   -> 13

       (Carola)      -> 7

       (Maximilian)  -> 8

       (Domas)       -> 2

       (Peter)       -> 4

       (Josua)       -> 9

       (Marc)        -> 10

       (Jiayao)      -> 11

  Presentations Dates:

       (Student)    -> Date  : (Paper)

   1 - (Marc)       -> 17/06 : (10) Calinon-10

   2 - (Erdenezul)  -> 17/06 : (3)  Pomerleau-89

   3 - (Jan)        -> 17/06 : (6)  Paraschos-13

   4 - (Carola)     -> 24/06 : (7)  Ratliff-06

   5 - (Domas)      -> 24/06 : (2)  Doerr-15

   6 - (Maximilian) -> 24/06 : (8)  Ziebart-08

   7 - (Katharina)  -> 01/07 : (13) Syed-08

   8 - (Jiayao)     -> 01/07 : (11) Mombaur-10

   9 - (Josua)      -> 01/07 : (9)  Boularias-11

  10 - (Peter)      -> 08/07 : (4)  Schaal-98

  11 - (Ralf)       -> 08/07 : (5)  Ijspeert-02

  12 - (Cihan)      -> 08/07 : (12) Levine-11

1 - @article{Englert:2017jv,

author = {Englert, Peter and Vien, Ngo Anh and Toussaint, Marc},

title = {{Inverse KKT: Learning cost functions of manipulation tasks from demonstrations}},

journal = {The International Journal of Robotics Research},

year = {2017}

exercise = {Implement a version without constraints of the algorithm on synthetic or real dataset}

}

2 - @article{Doerr2015,

author = {Doerr, Andreas and Ratliff, Nathan D and Bohg, Jeannette and Toussaint, Marc and Schaal, Stefan},

title = {{Direct Loss Minimization Inverse Optimal Control}},

year = {2015},

exercise = {Use an implementation of CMA-ES to solve a toy problem in grid world}

}

3 - @inproceedings{pomerleau1989alvinn,

  title={Alvinn: An autonomous land vehicle in a neural network},

  author={Pomerleau, Dean A},

  booktitle={Advances in neural information processing systems},

  year={1989},

  exercise = {Implement a version of the network in Tensorflow train an synthetic or real data}

}

4 - @article{schaal1998constructive,

  title={Constructive incremental learning from only local information},

  author={Schaal, Stefan and Atkeson, Christopher G},

  journal={Neural computation},

  year={1998},

  exercise = {Implement a version of the algorithm using the OpenAI Gym pole balancing environment}

}

5 - @inproceedings{ijspeert2002movement,

  title={Movement imitation with nonlinear dynamical systems in humanoid robots},

  author={Ijspeert, Auke Jan and Nakanishi, Jun and Schaal, Stefan},

  booktitle={Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No. 02CH37292)},

  year={2002},

  exercise = {Implement a version of the algorithm using the OpenAI Gym pole balancing environment}

}

6 - @inproceedings{paraschos2013probabilistic,

  title={Probabilistic movement primitives},

  author={Paraschos, Alexandros and Daniel, Christian and Peters, Jan R and Neumann, Gerhard},

  booktitle={Advances in neural information processing systems},

  year={2013},

  exercise = {Implement a version of the algorithm using the OpenAI Gym pole balancing environment}

}

7 - @inproceedings{ratliff2006maximum,

  title={Maximum margin planning},

  author={Ratliff, Nathan D and Bagnell, J Andrew and Zinkevich, Martin A},

  booktitle={Proceedings of the 23rd international conference on Machine learning},

  year={2006},

  exercise = {Implement a version of the algorithm on a grid world}

}

8 - @inproceedings{ziebart2008maximum,

  title={Maximum entropy inverse reinforcement learning},

  author={Ziebart, Brian D and Maas, Andrew L and Bagnell, J Andrew and Dey, Anind K},

  year={2008},

  exercise = {Implement a version of the algorithm on a grid world}

}

9 - @article{Boularias:2011wp,

author = {Boularias, A and Kober, J and Peters, J R},

title = {{Relative entropy inverse reinforcement learning}},

journal = {International {\ldots}},

year = {2011},

exercise = {Implement a version of the algorithm on a grid world}

}

10 - @article{calinon2010learning,

  title={Learning and reproduction of gestures by imitation},

  author={Calinon, Sylvain and D'halluin, Florent and Sauser, Eric L and Caldwell, Darwin G and Billard, Aude G},

  journal={IEEE Robotics \& Automation Magazine},

  year={2010},

  exercise = {Implement a version of the algorithm on a sythetic or real dataset}

}

11 - @article{Mombaur:2010hg,

author = {Mombaur, Katja and Truong, Anh and Laumond, Jean-Paul},

title = {{From human to humanoid locomotion an inverse optimal control approach}},

journal = {Autonomous Robots},

year = {2010},

exercise = {Implement a version of the algorithm on a synthetic or real dataset}

}

12 - @article{Levine:2011,

author = {Levine, Sergey},

title = {{Nonlinear Inverse Reinforcement Learning with Gaussian Processes}},

year = {2011},

exercise = {Implement a version of the algorithm on grid world}

}

13 - @book{Syed:2008fq,

author = {Syed, Umar and Bowling, Michael and Schapire, Robert E},

title = {{Apprenticeship learning using linear programming}},

publisher = {ACM},

year = {2008},

exercise = {Implement a version of the algorithm on grid world}

}