Abstract
We introduce agent-environment systems where the agent is stateful and executing a ReLU recurrent neural network. We define and study their verification problem by providing equivalences of recurrent and feed-forward neural networks on bounded execution traces. We give a sound and complete procedure for their verification against properties specified in a simplified version of LTL on bounded executions. We present an implementation and discuss the experimental results obtained.
Cite
CITATION STYLE
Akintunde, M. E., Kevorchian, A., Lomuscio, A., & Pirovano, E. (2019). Verification of RNN-based neural agent-environment systems. In 33rd AAAI Conference on Artificial Intelligence, AAAI 2019, 31st Innovative Applications of Artificial Intelligence Conference, IAAI 2019 and the 9th AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019 (pp. 6006–6013). AAAI Press. https://doi.org/10.1609/aaai.v33i01.33016006
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
