Mobilized ad-hoc networks: A reinforcement learning approach
Research in mobile ad-hoc networks has focused on situations in which nodes have no control over their movements. We investigate an important but overlooked domain in which nodes do have control over their movements. Reinforcement learning methods can be used to control both packet routing decisions...
| Main Authors: | , , |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/6732 |
| _version_ | 1826196014062632960 |
|---|---|
| author | Chang, Yu-Han Ho, Tracey Kaelbling, Leslie Pack |
| author_facet | Chang, Yu-Han Ho, Tracey Kaelbling, Leslie Pack |
| author_sort | Chang, Yu-Han |
| collection | MIT |
| description | Research in mobile ad-hoc networks has focused on situations in which nodes have no control over their movements. We investigate an important but overlooked domain in which nodes do have control over their movements. Reinforcement learning methods can be used to control both packet routing decisions and node mobility, dramatically improving the connectivity of the network. We first motivate the problem by presenting theoretical bounds for the connectivity improvement of partially mobile networks and then present superior empirical results under a variety of different scenarios in which the mobile nodes in our ad-hoc network are embedded with adaptive routing policies and learned movement policies. |
| first_indexed | 2024-09-23T10:19:27Z |
| id | mit-1721.1/6732 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T10:19:27Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/67322019-04-12T08:32:13Z Mobilized ad-hoc networks: A reinforcement learning approach Chang, Yu-Han Ho, Tracey Kaelbling, Leslie Pack AI reinforcement learning multi-agent learning ad-hoc networking Research in mobile ad-hoc networks has focused on situations in which nodes have no control over their movements. We investigate an important but overlooked domain in which nodes do have control over their movements. Reinforcement learning methods can be used to control both packet routing decisions and node mobility, dramatically improving the connectivity of the network. We first motivate the problem by presenting theoretical bounds for the connectivity improvement of partially mobile networks and then present superior empirical results under a variety of different scenarios in which the mobile nodes in our ad-hoc network are embedded with adaptive routing policies and learned movement policies. 2004-10-08T20:43:04Z 2004-10-08T20:43:04Z 2003-12-04 AIM-2003-025 http://hdl.handle.net/1721.1/6732 en_US AIM-2003-025 9 p. 771382 bytes 1199447 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | AI reinforcement learning multi-agent learning ad-hoc networking Chang, Yu-Han Ho, Tracey Kaelbling, Leslie Pack Mobilized ad-hoc networks: A reinforcement learning approach |
| title | Mobilized ad-hoc networks: A reinforcement learning approach |
| title_full | Mobilized ad-hoc networks: A reinforcement learning approach |
| title_fullStr | Mobilized ad-hoc networks: A reinforcement learning approach |
| title_full_unstemmed | Mobilized ad-hoc networks: A reinforcement learning approach |
| title_short | Mobilized ad-hoc networks: A reinforcement learning approach |
| title_sort | mobilized ad hoc networks a reinforcement learning approach |
| topic | AI reinforcement learning multi-agent learning ad-hoc networking |
| url | http://hdl.handle.net/1721.1/6732 |
| work_keys_str_mv | AT changyuhan mobilizedadhocnetworksareinforcementlearningapproach AT hotracey mobilizedadhocnetworksareinforcementlearningapproach AT kaelblinglesliepack mobilizedadhocnetworksareinforcementlearningapproach |