Exploration and Incentives in Reinforcement Learning.
Max SimchowitzAleksandrs SlivkinsPublished in: Oper. Res. (2024)
Keyphrases
- reinforcement learning
- active exploration
- exploration strategy
- action selection
- model based reinforcement learning
- exploration exploitation
- function approximation
- state space
- autonomous learning
- reinforcement learning algorithms
- model free
- exploration exploitation tradeoff
- markov decision processes
- neural network
- decision making
- dynamic programming
- learning process
- robotic control
- objective function
- temporal difference learning
- multi agent reinforcement learning
- learning algorithm
- real time
- real world
- genetic algorithm
- transition model
- markov decision process
- information visualization
- temporal difference
- optimal control
- supervised learning