Skip to Main content Skip to Navigation
Conference papers

Towards Multi-Agent Interactive Reinforcement Learning for Opportunistic Software Composition in Ambient Environments

Kévin Delcourt 1, 2 
Abstract : In order to manage the ever-growing number of devices present in modern and future ambient environments, as well as their dynamics and openness, we aim to propose a distributed multi-agent system that learns, in interaction with a human user, what would be their preferred applications given the services available. The goal of this Ph.D. thesis is to focus on the interaction between a reinforcement learning system and the human user, to improve the system's learning capabilities as well as the user's ease with the system, and ultimately build a working prototype, usable by end-users.
Complete list of metadata

https://ut3-toulouseinp.hal.science/hal-03682796
Contributor : Sylvie TROUILHET Connect in order to contact the contributor
Submitted on : Tuesday, May 31, 2022 - 11:56:46 AM
Last modification on : Monday, July 4, 2022 - 8:53:49 AM

File

p1839.pdf
Files produced by the author(s)

Identifiers

Citation

Kévin Delcourt. Towards Multi-Agent Interactive Reinforcement Learning for Opportunistic Software Composition in Ambient Environments. 21st International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2022), Doctoral Consortium, International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), May 2022, Auckland (virtual), New Zealand. pp.1839-1840, ⟨10.1145/3397271⟩. ⟨hal-03682796⟩

Share

Metrics

Record views

69

Files downloads

7