Breaking the Split Incentive Hurdle via Time-Varying Monetary Rewards.
Yong ZhanDu XuHongfang YuShui YuPublished in: GLOBECOM (2016)
Keyphrases
- free riding
- incentive mechanism
- markov decision processes
- reinforcement learning
- multiarmed bandit
- short term
- artificial intelligence
- bandit problems
- credit assignment
- long term
- reward function
- decision makers
- multi armed bandits
- adverse selection
- real time
- dynamic programming
- evolutionary algorithm
- cooperative
- information retrieval
- machine learning
- neural network