Back to Search
Start Over
Learning from Demonstrations: Is It Worth Estimating a Reward Function?
- Source :
- Advanced Information Systems Engineering ISBN: 9783642387081, ECML/PKDD (1), 1st Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM 2013), 1st Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM 2013), Oct 2013, Princeton, New Jersey, United States, Lecture Notes in Computer Science, Joint European Conference on Machine Learning and Knowledge Discovery in Databases (ECML/PKDD 2013), Joint European Conference on Machine Learning and Knowledge Discovery in Databases (ECML/PKDD 2013), Sep 2013, Prague, Czech Republic. pp.17-32, ⟨10.1007/978-3-642-40988-2_2⟩
- Publication Year :
- 2013
- Publisher :
- Springer Berlin Heidelberg, 2013.
-
Abstract
- International audience; This paper provides a comparative study between Inverse Reinforcement Learning (IRL) and Apprenticeship Learning (AL). IRL and AL are two frameworks, using Markov Decision Processes (MDP), which are used for the imitation learning problem where an agent tries to learn from demonstrations of an expert. In the AL Framework, the agent tries to learn the expert policy whereas in the IRL Framework, the agent tries to learn a reward which can explain the behavior of the expert. This reward is then optimized to imitate the expert. One can wonder if it is worth estimating such a reward, or if estimating a Policy is sufficient. This quite natural question has not really been addressed in the literature right now. We provide partial answers, both from a theoretical and empirical point of view.
- Subjects :
- Point (typography)
Computer science
business.industry
media_common.quotation_subject
02 engineering and technology
010501 environmental sciences
Imitation learning
Machine learning
computer.software_genre
01 natural sciences
Wonder
[STAT.ML]Statistics [stat]/Machine Learning [stat.ML]
Apprenticeship learning
Inverse reinforcement learning
0202 electrical engineering, electronic engineering, information engineering
Natural (music)
020201 artificial intelligence & image processing
Markov decision process
Artificial intelligence
Function (engineering)
business
computer
0105 earth and related environmental sciences
media_common
Subjects
Details
- ISBN :
- 978-3-642-38708-1
- ISBNs :
- 9783642387081
- Database :
- OpenAIRE
- Journal :
- Advanced Information Systems Engineering ISBN: 9783642387081, ECML/PKDD (1), 1st Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM 2013), 1st Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM 2013), Oct 2013, Princeton, New Jersey, United States, Lecture Notes in Computer Science, Joint European Conference on Machine Learning and Knowledge Discovery in Databases (ECML/PKDD 2013), Joint European Conference on Machine Learning and Knowledge Discovery in Databases (ECML/PKDD 2013), Sep 2013, Prague, Czech Republic. pp.17-32, ⟨10.1007/978-3-642-40988-2_2⟩
- Accession number :
- edsair.doi.dedup.....970a5d83a756fe77211aa090b8f6ee30