Interpretable and Editable Programmatic ...
Document type :
Communication dans un congrès avec actes
Permalink :
Title :
Interpretable and Editable Programmatic Tree Policies for Reinforcement Learning
Author(s) :
Kohler, Hector [Auteur]
Université de Lille
Centrale Lille
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Scool [Scool]
Delfosse, Quentin [Auteur]
Technische Universität Darmstadt - Technical University of Darmstadt [TU Darmstadt]
Akrour, Riad [Auteur]
Université de Lille
Centrale Lille
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Scool [Scool]
Kersting, Kristian [Auteur]
Technische Universität Darmstadt - Technical University of Darmstadt [TU Darmstadt]
Preux, Philippe [Auteur]
Université de Lille
Centrale Lille
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Scool [Scool]
Université de Lille
Centrale Lille
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Scool [Scool]
Delfosse, Quentin [Auteur]
Technische Universität Darmstadt - Technical University of Darmstadt [TU Darmstadt]
Akrour, Riad [Auteur]
Université de Lille
Centrale Lille
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Scool [Scool]
Kersting, Kristian [Auteur]
Technische Universität Darmstadt - Technical University of Darmstadt [TU Darmstadt]
Preux, Philippe [Auteur]

Université de Lille
Centrale Lille
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Scool [Scool]
Conference title :
European Workshop on Reinforcement Learning
City :
Toulouse
Country :
France
Start date of the conference :
2024-10-28
Publication date :
2024
English keyword(s) :
Interpretable AI
Reinforcement Learning
Decision Tree
Reinforcement Learning
Decision Tree
HAL domain(s) :
Informatique [cs]/Intelligence artificielle [cs.AI]
English abstract : [en]
Deep reinforcement learning agents are prone to goal misalignments. The black-box nature of their policies hinders the detection and correction of such misalignments, and the trust necessary for real-world deployment. So ...
Show more >Deep reinforcement learning agents are prone to goal misalignments. The black-box nature of their policies hinders the detection and correction of such misalignments, and the trust necessary for real-world deployment. So far, solutions learning interpretable policies are inefficient or require many human priors. We propose INTERPRETER, a fast distillation method producing INTerpretable Editable tRee Programs for ReinforcEmenT lEaRning. We empirically demonstrate that INTERPRETER compact tree programs match oracles across a diverse set of sequential decision tasks and evaluate the impact of our design choices on interpretability and performances. We show that our policies can be interpreted and edited to correct misalignments on Atari games and to explain real farming strategies.Show less >
Show more >Deep reinforcement learning agents are prone to goal misalignments. The black-box nature of their policies hinders the detection and correction of such misalignments, and the trust necessary for real-world deployment. So far, solutions learning interpretable policies are inefficient or require many human priors. We propose INTERPRETER, a fast distillation method producing INTerpretable Editable tRee Programs for ReinforcEmenT lEaRning. We empirically demonstrate that INTERPRETER compact tree programs match oracles across a diverse set of sequential decision tasks and evaluate the impact of our design choices on interpretability and performances. We show that our policies can be interpreted and edited to correct misalignments on Atari games and to explain real farming strategies.Show less >
Language :
Anglais
Peer reviewed article :
Oui
Audience :
Internationale
Popular science :
Non
Collections :
Source :
Submission date :
2024-11-16T03:31:38Z
Files
- document
- Open access
- Access the document
- Interpretable_and_Editable_.pdf
- Open access
- Access the document