Regret Bounds for Reinforcement Learning ...
Document type :
Communication dans un congrès avec actes
Title :
Regret Bounds for Reinforcement Learning with Policy Advice
Author(s) :
Gheshlaghi Azar, Mohammad [Auteur]
Computer Science Department - Carnegie Mellon University
Lazaric, Alessandro [Auteur]
Laboratoire d'Informatique Fondamentale de Lille [LIFL]
Sequential Learning [SEQUEL]
Brunskill, Emma [Auteur]
Computer Science Department - Carnegie Mellon University
Computer Science Department - Carnegie Mellon University
Lazaric, Alessandro [Auteur]
Laboratoire d'Informatique Fondamentale de Lille [LIFL]
Sequential Learning [SEQUEL]
Brunskill, Emma [Auteur]
Computer Science Department - Carnegie Mellon University
Conference title :
ECML/PKDD - European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases
City :
Prague
Country :
République tchèque
Start date of the conference :
2013-09
Publication date :
2013-09
HAL domain(s) :
Informatique [cs]/Apprentissage [cs.LG]
English abstract : [en]
In some reinforcement learning problems an agent may be provided with a set of input policies, perhaps learned from prior experience or provided by advisors. We present a reinforcement learning with policy advice (RLPA) ...
Show more >In some reinforcement learning problems an agent may be provided with a set of input policies, perhaps learned from prior experience or provided by advisors. We present a reinforcement learning with policy advice (RLPA) algorithm which leverages this input set and learns to use the best policy in the set for the reinforcement learning task at hand. We prove that RLPA has a sub-linear regret of $\widetilde O(\sqrt{T})$ relative to the best input policy, and that both this regret and its computational complexity are independent of the size of the state and action space. Our empirical simulations support our theoretical analysis. This suggests RLPA may offer significant advantages in large domains where some prior good policies are provided.Show less >
Show more >In some reinforcement learning problems an agent may be provided with a set of input policies, perhaps learned from prior experience or provided by advisors. We present a reinforcement learning with policy advice (RLPA) algorithm which leverages this input set and learns to use the best policy in the set for the reinforcement learning task at hand. We prove that RLPA has a sub-linear regret of $\widetilde O(\sqrt{T})$ relative to the best input policy, and that both this regret and its computational complexity are independent of the size of the state and action space. Our empirical simulations support our theoretical analysis. This suggests RLPA may offer significant advantages in large domains where some prior good policies are provided.Show less >
Language :
Anglais
Peer reviewed article :
Oui
Audience :
Internationale
Popular science :
Non
European Project :
Collections :
Source :
Files
- https://hal.inria.fr/hal-00924021/document
- Open access
- Access the document
- https://hal.inria.fr/hal-00924021/document
- Open access
- Access the document
- https://hal.inria.fr/hal-00924021/document
- Open access
- Access the document