Contextual Bandits Evolving Over Finite Time
| Autor: | Sharayu Moharir, Vishal Jain, Harsh Deshpande |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Structure (mathematical logic) Computer Science - Machine Learning Context model Mathematical optimization Computer science Stochastic matrix Machine Learning (stat.ML) Regret Machine Learning (cs.LG) Matrix (mathematics) Statistics - Machine Learning Finite time Externality |
| Zdroj: | COMSNETS |
| DOI: | 10.1109/comsnets48256.2020.9027425 |
| Popis: | Contextual bandits have the same exploration-exploitation trade-off as standard multi-armed bandits. On adding positive externalities that decay with time, this problem becomes much more difficult as wrong decisions at the start are hard to recover from. We explore existing policies in this setting and highlight their biases towards the inherent reward matrix. We propose a rejection based policy that achieves a low regret irrespective of the structure of the reward probability matrix. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|