How do Offline Measures for Exploration in Reinforcement Learning behave?
Jakob J. HollensteinSayantan AuddyMatteo SaverianoErwan RenaudoJustus H. PiaterPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- active exploration
- exploration strategy
- model based reinforcement learning
- function approximation
- action selection
- real time
- autonomous learning
- exploration exploitation
- state space
- neural network
- exploration exploitation tradeoff
- reinforcement learning methods
- multi agent
- learning algorithm
- evaluation measures
- model free
- markov decision processes
- temporal difference
- reinforcement learning algorithms
- mobile robot
- active learning
- policy search
- case study
- robotic control
- genetic algorithm
- machine learning