Context Transfer in Reinforcement Learning Using Action-Value Functions
Joint Authors
Araabi, Babak N.
Mousavi, Amin
Nili Ahmadabadi, Majid
Source
Computational Intelligence and Neuroscience
Issue
Vol. 2014, Issue 2014 (31 Dec. 2014), pp.1-10, 10 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2014-12-30
Country of Publication
Egypt
No. of Pages
10
Main Subjects
Abstract EN
This paper discusses the notion of context transfer in reinforcement learning tasks.
Context transfer, as defined in this paper, implies knowledge transfer between source and target tasks that share the same environment dynamics and reward function but have different states or action spaces.
In other words, the agents learn the same task while using different sensors and actuators.
This requires the existence of an underlying common Markov decision process (MDP) to which all the agents’ MDPs can be mapped.
This is formulated in terms of the notion of MDP homomorphism.
The learning framework is Q -learning.
To transfer the knowledge between these tasks, the feature space is used as a translator and is expressed as a partial mapping between the state-action spaces of different tasks.
The Q -values learned during the learning process of the source tasks are mapped to the sets of Q -values for the target task.
These transferred Q -values are merged together and used to initialize the learning process of the target task.
An interval-based approach is used to represent and merge the knowledge of the source tasks.
Empirical results show that the transferred initialization can be beneficial to the learning process of the target task.
American Psychological Association (APA)
Mousavi, Amin& Araabi, Babak N.& Nili Ahmadabadi, Majid. 2014. Context Transfer in Reinforcement Learning Using Action-Value Functions. Computational Intelligence and Neuroscience،Vol. 2014, no. 2014, pp.1-10.
https://search.emarefa.net/detail/BIM-1034647
Modern Language Association (MLA)
Mousavi, Amin…[et al.]. Context Transfer in Reinforcement Learning Using Action-Value Functions. Computational Intelligence and Neuroscience No. 2014 (2014), pp.1-10.
https://search.emarefa.net/detail/BIM-1034647
American Medical Association (AMA)
Mousavi, Amin& Araabi, Babak N.& Nili Ahmadabadi, Majid. Context Transfer in Reinforcement Learning Using Action-Value Functions. Computational Intelligence and Neuroscience. 2014. Vol. 2014, no. 2014, pp.1-10.
https://search.emarefa.net/detail/BIM-1034647
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1034647