Demo2Test: Transfer Testing of Agent in Competitive Environment with Failure Demonstrations
Saved in:
| Title: | Demo2Test: Transfer Testing of Agent in Competitive Environment with Failure Demonstrations |
|---|---|
| Authors: | Jianming Chen, Yawen Wang, Junjie Wang, Xiaofei Xie, Dandan Wang, Qing Wang, Fanjiang Xu |
| Source: | ACM Transactions on Software Engineering and Methodology. 34:1-28 |
| Publisher Information: | Association for Computing Machinery (ACM), 2025. |
| Publication Year: | 2025 |
| Subject Terms: | Transfer Reinforcement Learning, Theory and Algorithms, Software Engineering, Key State Perturbation, Testing Diversity, Adversarial Agent Testing |
| Description: | The competitive game between agents exists in many critical applications, such as military unmanned aerial vehicles. It is urgent to test these agents to reduce the significant losses caused by their failures. Existing studies mainly are to construct a testing agent that competes with the target agent to induce its failures. These approaches usually focus on a single task, requiring much more time for multi-task testing. However, if the previously tested tasks (source tasks) and the task to be tested (target task) share similar agents or task objectives, the transferable knowledge in source tasks can potentially increase the effectiveness of testing in the target task. We propose Demo2Test for conducting transfer testing of agents in the competitive environment, i.e., leveraging the demonstrations of failure scenarios from the source task to boost the testing effectiveness in the target task. It trains a testing agent with demonstrations and incorporates the action perturbation at key states to balance the number of revealed failures and their diversity. We conduct experiments in the simulated robotics competitive environments of MuJoCo. The results indicate that Demo2Test outperforms the best-performing baseline with improvements ranging from \(22.38\%\) to \(87.98\%\) , and \(12.69\%\) to \(60.98\%\) , in terms of the number and diversity of discovered failure scenarios, respectively. |
| Document Type: | Article |
| File Description: | application/pdf |
| Language: | English |
| ISSN: | 1557-7392 1049-331X |
| DOI: | 10.1145/3696001 |
| Rights: | CC BY CC BY NC ND |
| Accession Number: | edsair.doi.dedup.....e40e65b3f739b5f3364816c14e368db8 |
| Database: | OpenAIRE |
Full Text Finder 
Nájsť tento článok vo Web of Science | Abstract: | The competitive game between agents exists in many critical applications, such as military unmanned aerial vehicles. It is urgent to test these agents to reduce the significant losses caused by their failures. Existing studies mainly are to construct a testing agent that competes with the target agent to induce its failures. These approaches usually focus on a single task, requiring much more time for multi-task testing. However, if the previously tested tasks (source tasks) and the task to be tested (target task) share similar agents or task objectives, the transferable knowledge in source tasks can potentially increase the effectiveness of testing in the target task. We propose Demo2Test for conducting transfer testing of agents in the competitive environment, i.e., leveraging the demonstrations of failure scenarios from the source task to boost the testing effectiveness in the target task. It trains a testing agent with demonstrations and incorporates the action perturbation at key states to balance the number of revealed failures and their diversity. We conduct experiments in the simulated robotics competitive environments of MuJoCo. The results indicate that Demo2Test outperforms the best-performing baseline with improvements ranging from \(22.38\%\) to \(87.98\%\) , and \(12.69\%\) to \(60.98\%\) , in terms of the number and diversity of discovered failure scenarios, respectively. |
|---|---|
| ISSN: | 15577392 1049331X |
| DOI: | 10.1145/3696001 |