Open Access
Peer-Reviewed
Foundational Models & Architectures
Using “social Actions” and Rl- Algorithms to Build Policies in Dec- Pomdp
Abstract
Building individual behaviors to solve collective pr oblems is a major stake whose applications are found in several domains. To do so, Dec-POMDP has b een proposed as a formalism for describing multi-agent problems. However, solving a Dec-POMDP turned out to be a NEXP problem. In this study, we introduced the original concept of social action to get round the inherent complexity of Dec-POMDP and we proposed three decentralized reinf orcement learning algorithms which approximate the optimal policy in Dec-POMDP. This a rticle analyses the results obtained and argues that this new approach seems promising for a utomatic top-down collective behavior computation..
Keywords
Multi-agent systems
Markov decision processes
reinforcement learning
interaction.
Declarations & Ethics
Funding:
This research received academic dissemination support through ESCAP / JournalsHub publishing programs.
Conflicts of Interest:
The authors declare no competing financial or institutional interests.
Peer Review:
Double-blind peer reviewed by international subject specialists.
License:
Creative Commons Attribution 4.0 International (CC BY 4.0).
How to Cite This Article
APA / MLA / BibTeX
Nancy, et al. (2009). Using “social Actions” and Rl- Algorithms to Build Policies in Dec- Pomdp. IADIS International Journal on Computer Science and Information Systems, 4(3). https://doi.org/10.33965/ijcsis_2009_v4i3_07
Nancy, et al. "Using “social Actions” and Rl- Algorithms to Build Policies in Dec- Pomdp." IADIS International Journal on Computer Science and Information Systems, vol. 4, no. 3, 2009. https://doi.org/10.33965/ijcsis_2009_v4i3_07
Nancy, et al. "Using “social Actions” and Rl- Algorithms to Build Policies in Dec- Pomdp." IADIS International Journal on Computer Science and Information Systems 4, no. 3 (2009). https://doi.org/10.33965/ijcsis_2009_v4i3_07