ATENA-PRO: Generating Personalized Exploration Notebooks with Constrained Reinforcement Learning.
Tavor LipmanTova MiloAmit SomechPublished in: SIGMOD Conference Companion (2023)
Keyphrases
- reinforcement learning
- active exploration
- exploration strategy
- action selection
- model based reinforcement learning
- function approximation
- autonomous learning
- adaptive learning
- exploration exploitation
- learning algorithm
- markov decision processes
- state space
- reinforcement learning algorithms
- optimal policy
- user profiles
- model free
- neural network
- automatically generating
- exploration exploitation tradeoff
- user modeling
- learning process
- e learning
- temporal difference
- user centric
- personalized search
- learning classifier systems
- optimal control
- multi agent