Near-Optimal Adversarial Policy Switching for Decentralized Asynchronous Multi-Agent Systems
© 2018 IEEE. A key challenge in multi-robot and multi-agent systems is generating solutions that are robust to other self-interested or even adversarial parties who actively try to prevent the agents from achieving their goals. The practicality of existing works addressing this challenge is limited...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021
|
| Online Access: | https://hdl.handle.net/1721.1/137872 |
| _version_ | 1826217849433096192 |
|---|---|
| author | Hoang, Trong Nghia Hoang Xiao, Yuchen Sivakumar, Kavinayan Amato, Christopher How, Jonathan P. |
| author2 | Massachusetts Institute of Technology. Laboratory for Information and Decision Systems |
| author_facet | Massachusetts Institute of Technology. Laboratory for Information and Decision Systems Hoang, Trong Nghia Hoang Xiao, Yuchen Sivakumar, Kavinayan Amato, Christopher How, Jonathan P. |
| author_sort | Hoang, Trong Nghia Hoang |
| collection | MIT |
| description | © 2018 IEEE. A key challenge in multi-robot and multi-agent systems is generating solutions that are robust to other self-interested or even adversarial parties who actively try to prevent the agents from achieving their goals. The practicality of existing works addressing this challenge is limited to only small-scale synchronous decision-making scenarios or a single agent planning its best response against a single adversary with fixed, procedurally characterized strategies. In contrast this paper considers a more realistic class of problems where a team of asynchronous agents with limited observation and communication capabilities need to compete against multiple strategic adversaries with changing strategies. This problem necessitates agents that can coordinate to detect changes in adversary strategies and plan the best response accordingly. Our approach first optimizes a set of stratagems that represent these best responses. These optimized stratagems are then integrated into a unified policy that can detect and respond when the adversaries change their strategies. The near-optimality of the proposed framework is established theoretically as well as demonstrated empirically in simulation and hardware. |
| first_indexed | 2024-09-23T17:10:09Z |
| format | Article |
| id | mit-1721.1/137872 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T17:10:09Z |
| publishDate | 2021 |
| publisher | IEEE |
| record_format | dspace |
| spelling | mit-1721.1/1378722023-02-13T21:18:21Z Near-Optimal Adversarial Policy Switching for Decentralized Asynchronous Multi-Agent Systems Hoang, Trong Nghia Hoang Xiao, Yuchen Sivakumar, Kavinayan Amato, Christopher How, Jonathan P. Massachusetts Institute of Technology. Laboratory for Information and Decision Systems © 2018 IEEE. A key challenge in multi-robot and multi-agent systems is generating solutions that are robust to other self-interested or even adversarial parties who actively try to prevent the agents from achieving their goals. The practicality of existing works addressing this challenge is limited to only small-scale synchronous decision-making scenarios or a single agent planning its best response against a single adversary with fixed, procedurally characterized strategies. In contrast this paper considers a more realistic class of problems where a team of asynchronous agents with limited observation and communication capabilities need to compete against multiple strategic adversaries with changing strategies. This problem necessitates agents that can coordinate to detect changes in adversary strategies and plan the best response accordingly. Our approach first optimizes a set of stratagems that represent these best responses. These optimized stratagems are then integrated into a unified policy that can detect and respond when the adversaries change their strategies. The near-optimality of the proposed framework is established theoretically as well as demonstrated empirically in simulation and hardware. 2021-11-09T14:03:59Z 2021-11-09T14:03:59Z 2017-10 2019-10-28T16:59:25Z Article http://purl.org/eprint/type/ConferencePaper https://hdl.handle.net/1721.1/137872 Hoang, Trong Nghia Hoang, Xiao, Yuchen, Sivakumar, Kavinayan, Amato, Christopher and How, Jonathan P. 2017. "Near-Optimal Adversarial Policy Switching for Decentralized Asynchronous Multi-Agent Systems." en 10.1109/ICRA.2018.8460485 Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf IEEE arXiv |
| spellingShingle | Hoang, Trong Nghia Hoang Xiao, Yuchen Sivakumar, Kavinayan Amato, Christopher How, Jonathan P. Near-Optimal Adversarial Policy Switching for Decentralized Asynchronous Multi-Agent Systems |
| title | Near-Optimal Adversarial Policy Switching for Decentralized Asynchronous Multi-Agent Systems |
| title_full | Near-Optimal Adversarial Policy Switching for Decentralized Asynchronous Multi-Agent Systems |
| title_fullStr | Near-Optimal Adversarial Policy Switching for Decentralized Asynchronous Multi-Agent Systems |
| title_full_unstemmed | Near-Optimal Adversarial Policy Switching for Decentralized Asynchronous Multi-Agent Systems |
| title_short | Near-Optimal Adversarial Policy Switching for Decentralized Asynchronous Multi-Agent Systems |
| title_sort | near optimal adversarial policy switching for decentralized asynchronous multi agent systems |
| url | https://hdl.handle.net/1721.1/137872 |
| work_keys_str_mv | AT hoangtrongnghiahoang nearoptimaladversarialpolicyswitchingfordecentralizedasynchronousmultiagentsystems AT xiaoyuchen nearoptimaladversarialpolicyswitchingfordecentralizedasynchronousmultiagentsystems AT sivakumarkavinayan nearoptimaladversarialpolicyswitchingfordecentralizedasynchronousmultiagentsystems AT amatochristopher nearoptimaladversarialpolicyswitchingfordecentralizedasynchronousmultiagentsystems AT howjonathanp nearoptimaladversarialpolicyswitchingfordecentralizedasynchronousmultiagentsystems |