Intent Demonstration in General-Sum Dynamic Games via Iterative Linear-Quadratic Approximations
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911254409379840 |
|---|---|
| author | Li, Jingqi Siththaranjan, Anand Sojoudi, Somayeh Tomlin, Claire Bajcsy, Andrea |
| author_facet | Li, Jingqi Siththaranjan, Anand Sojoudi, Somayeh Tomlin, Claire Bajcsy, Andrea |
| contents | Autonomous agents should coordinate effectively without prior knowledge of others' intents. While prior work has focused on intent inference, we address the inverse problem: how agents can strategically demonstrate their intents within general-sum dynamic games. We model this problem and propose an algorithm that balances intent demonstration with task performance. To handle nonlinear dynamic games with continuous state-action spaces, our method leverages iterative linear-quadratic game approximations and provides efficient intent-teaching guarantees: the uncertain agent's belief can be driven rapidly to the ground truth, while the demonstrating agent avoids expending effort on unnecessary belief alignment when it does not improve task performance. Theoretical analysis and hardware experiments confirm that our approach enables the demonstrating agent to reconcile task execution with belief alignment and strategically manage the information asymmetry among agents, even as its intent evolves during deployment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_10182 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Intent Demonstration in General-Sum Dynamic Games via Iterative Linear-Quadratic Approximations Li, Jingqi Siththaranjan, Anand Sojoudi, Somayeh Tomlin, Claire Bajcsy, Andrea Systems and Control Autonomous agents should coordinate effectively without prior knowledge of others' intents. While prior work has focused on intent inference, we address the inverse problem: how agents can strategically demonstrate their intents within general-sum dynamic games. We model this problem and propose an algorithm that balances intent demonstration with task performance. To handle nonlinear dynamic games with continuous state-action spaces, our method leverages iterative linear-quadratic game approximations and provides efficient intent-teaching guarantees: the uncertain agent's belief can be driven rapidly to the ground truth, while the demonstrating agent avoids expending effort on unnecessary belief alignment when it does not improve task performance. Theoretical analysis and hardware experiments confirm that our approach enables the demonstrating agent to reconcile task execution with belief alignment and strategically manage the information asymmetry among agents, even as its intent evolves during deployment. |
| title | Intent Demonstration in General-Sum Dynamic Games via Iterative Linear-Quadratic Approximations |
| topic | Systems and Control |
| url | https://arxiv.org/abs/2402.10182 |