Gradient-based minimization for multi-expert Inverse Reinforcement Learning
(2017) 2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 In 2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings 2018-January. p.1-8- Abstract
We present a model-free method for solving the Inverse Reinforcement Learning (IRL) problem given a set of trajectories generated by different experts' policies. In many applications, the observed demonstrations are not produced by the same policy. In fact, they may be provided by multiple experts that follow different (but similar) policies or even by the same expert that does not always replicate the same policy (e.g., human expert). We propose to model different experts' demonstrations as generated by policies sampled from a distribution. Differently from many other IRL approaches, the proposed methodology requires neither knowledge about the dynamics of the system nor to iteratively solve the direct problem for different candidate... (More)
We present a model-free method for solving the Inverse Reinforcement Learning (IRL) problem given a set of trajectories generated by different experts' policies. In many applications, the observed demonstrations are not produced by the same policy. In fact, they may be provided by multiple experts that follow different (but similar) policies or even by the same expert that does not always replicate the same policy (e.g., human expert). We propose to model different experts' demonstrations as generated by policies sampled from a distribution. Differently from many other IRL approaches, the proposed methodology requires neither knowledge about the dynamics of the system nor to iteratively solve the direct problem for different candidate reward functions, thus providing an efficient solution to the IRL problem.
(Less)
- author
- Tateo, Davide
LU
; Pirotta, Matteo
; Restelli, Marcello
and Bonarini, Andrea
- publishing date
- 2017-07-01
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- 2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings
- series title
- 2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings
- volume
- 2018-January
- pages
- 8 pages
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- conference name
- 2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017
- conference location
- Honolulu, United States
- conference dates
- 2017-11-27 - 2017-12-01
- external identifiers
-
- scopus:85046080056
- ISBN
- 9781538627259
- DOI
- 10.1109/SSCI.2017.8280919
- language
- English
- LU publication?
- no
- id
- 8ee9154b-47d1-4e8c-b667-906e816be220
- date added to LUP
- 2025-10-16 14:43:38
- date last changed
- 2025-10-24 03:39:46
@inproceedings{8ee9154b-47d1-4e8c-b667-906e816be220,
abstract = {{<p>We present a model-free method for solving the Inverse Reinforcement Learning (IRL) problem given a set of trajectories generated by different experts' policies. In many applications, the observed demonstrations are not produced by the same policy. In fact, they may be provided by multiple experts that follow different (but similar) policies or even by the same expert that does not always replicate the same policy (e.g., human expert). We propose to model different experts' demonstrations as generated by policies sampled from a distribution. Differently from many other IRL approaches, the proposed methodology requires neither knowledge about the dynamics of the system nor to iteratively solve the direct problem for different candidate reward functions, thus providing an efficient solution to the IRL problem.</p>}},
author = {{Tateo, Davide and Pirotta, Matteo and Restelli, Marcello and Bonarini, Andrea}},
booktitle = {{2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings}},
isbn = {{9781538627259}},
language = {{eng}},
month = {{07}},
pages = {{1--8}},
publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
series = {{2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings}},
title = {{Gradient-based minimization for multi-expert Inverse Reinforcement Learning}},
url = {{http://dx.doi.org/10.1109/SSCI.2017.8280919}},
doi = {{10.1109/SSCI.2017.8280919}},
volume = {{2018-January}},
year = {{2017}},
}