Formal Verification of Parameterised Neural-symbolic Multi-agent Systems
Authors: Panagiotis Kouvaros, Elena Botoeva, Cosmo De Bonis-Campbell
IJCAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We present an implementation and discuss experimental results obtained on a social dilemma game based on guarding. |
| Researcher Affiliation | Academia | Panagiotis Kouvaros1 , Elena Botoeva2 and Cosmo De Bonis-Campbell2 1Technology and Innovation School, University of Limassol 2School of Computing, University of Kent |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper mentions using the "VENMAS toolkit [Akintunde et al., 2020b]" but does not state that the authors are releasing their own code for the methodology described in this paper. |
| Open Datasets | No | The paper describes training a neural observation function within a simulated game environment, but it does not provide concrete access information for a publicly available or open dataset. |
| Dataset Splits | No | The paper describes training an agent in a simulated game but does not specify dataset splits (e.g., train/validation/test percentages or counts) needed to reproduce data partitioning. |
| Hardware Specification | Yes | The experiments were performed on a standard PC running Ubuntu 22.04 with 16GB RAM and processor Intel(R) Core i5-4460. |
| Software Dependencies | Yes | The experiments were performed on a standard PC running Ubuntu 22.04 with 16GB RAM and processor Intel(R) Core i5-4460. We relied on Gurobi v10.0 [Gu et al., 2016] to solve the mixed integer linear programs generated by VENMAS. |
| Experiment Setup | Yes | During the training, the game was played by 4 agents, and the parameters were set as Mh = 4, Gr = 2, Rr = 1 and Ur = 3. The produced neural network has two hidden layers of four Re LU activated neurons, takes as input a single neuron, representing the normalised health points of the agent, and outputs the estimated Q-values of the two actions rest and guard . |