Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2409.12397 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918133136097280 |
|---|---|
| author | Chen, Shenghui Zhu, Shufang De Giacomo, Giuseppe Topcu, Ufuk |
| author_facet | Chen, Shenghui Zhu, Shufang De Giacomo, Giuseppe Topcu, Ufuk |
| contents | Achieving seamless coordination in cooperative games is a crucial challenge in artificial intelligence, particularly when players operate under incomplete information. While communication helps, it is not always feasible. In this paper, we explore how effective coordination can be achieved without verbal communication, relying solely on observing each other's actions. Our method enables an agent to develop a strategy by interpreting its partner's action sequences as intent signals, constructing a finite-state transducer built from deterministic finite automata, one for each possible action the agent can take. Experiments show that these strategies significantly outperform uncoordinated ones and closely match the performance of coordinating via direct communication. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_12397 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Learning to Coordinate without Communication under Incomplete Information Chen, Shenghui Zhu, Shufang De Giacomo, Giuseppe Topcu, Ufuk Artificial Intelligence Achieving seamless coordination in cooperative games is a crucial challenge in artificial intelligence, particularly when players operate under incomplete information. While communication helps, it is not always feasible. In this paper, we explore how effective coordination can be achieved without verbal communication, relying solely on observing each other's actions. Our method enables an agent to develop a strategy by interpreting its partner's action sequences as intent signals, constructing a finite-state transducer built from deterministic finite automata, one for each possible action the agent can take. Experiments show that these strategies significantly outperform uncoordinated ones and closely match the performance of coordinating via direct communication. |
| title | Learning to Coordinate without Communication under Incomplete Information |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2409.12397 |