Name
Abstract | ||
|---|---|---|
With rapid growth of shareable bikes comes the problem of indiscriminately parked bikes blocking traffic. We propose a centralized pricing based dynamic incentive mechanism to mobilize the participants via crowdsourcing with regarding to reposition the indiscriminately parked bikes. We formalize the key component of the proposed incentive mechanism into two decision-making model: individual decision-making model Cost-refundable, Multiple Resources Constrained Multiple Armed Bandit (CRMR-MAB) and overall decision-making model multi-dimensional and multiple choice Knapsack problem (MMKP). We proposed a comprehensive decision algorithm GA-WSLS which combines the two. Realistic simulation based on real-world dataset from Singapore demonstrated significant advantages of the proposed approach over 7 existing approaches. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.5555/3306127.3332023 | adaptive agents and multi-agents systems |
Keywords | Field | DocType |
Crowdsourcing,Multi-Armed Bandit,Multi-dimensional Multiple Choice Knapsack Problem | Incentive,Computer science,Multiple choice knapsack problem,Crowdsourcing,Operations research,Artificial intelligence,Multi-armed bandit,Machine learning | Conference |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
5 | ||