Tabular and Deep Reinforcement Learning for Gittins Index.
Harshit DhankarKshitij MishraTejas BodasPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- learning algorithm
- state space
- index structure
- function approximation
- real time
- learning process
- reinforcement learning algorithms
- temporal difference
- action selection
- structural similarity
- partially observable
- markov decision processes
- transfer learning
- temporal difference learning
- case study
- information systems
- database
- deep learning
- policy search
- indexing method
- dynamic allocation
- model free
- inverted index
- optimal control
- b tree
- optimal policy
- supervised learning
- machine learning