Silk: A Simulation Study of Regulating Open Normative Multiagent Systems
Authors: Mehdi Mashayekhi, Hongying Du, George F. List, Munindar P. Singh
IJCAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We evaluate Silk via simulation in the traffic domain. Our results show that social norms promoting conflict resolution emerge in both moderate and selfish societies via our hybrid mechanism. |
| Researcher Affiliation | Academia | Mehdi Mashayekhi, Hongying Du, George F. List, Munindar P. Singh North Carolina State University, Raleigh, NC 27695, USA {mmashay2, hdu2, gflist, singh}@ncsu.edu |
| Pseudocode | Yes | Algorithm 1 shows how the generator generates norms and laws. Algorithm 2 shows how the members interact. |
| Open Source Code | No | The paper does not provide an explicit statement or link indicating that the source code for the methodology is openly available. |
| Open Datasets | No | The paper describes a simulation study using a 'simulated traffic system' within 'Repast [Morales et al., 2013; North et al., 2013]' and defines its own 'payoff matrices' for the simulation. It does not use or provide a publicly available dataset in the traditional sense. |
| Dataset Splits | No | The paper describes a simulation study where reinforcement learning is applied and results are averaged over trials, but it does not specify explicit training, validation, or test dataset splits. |
| Hardware Specification | No | The paper states it uses a 'simulated traffic system' in 'Repast' but provides no specific details regarding the hardware used for running the simulations. |
| Software Dependencies | No | The paper mentions the use of 'Repast' as a simulation environment, but it does not provide specific version numbers for Repast or any other software dependencies. |
| Experiment Setup | Yes | We initialize utilities to zero at t = 0 and set in formula (1) to 0.2. We set E = 0.05 in the exponential function (e Em), which we use for the -greedy approach. The data shows average over 1,000 trials. For the fully actuated control strategy, minimum green is set to one tick and the gap time is set to zero, and Maximum green is considered five ticks. |