Model-Free Active Exploration in Reinforcement Learning.
Alessio RussoAlexandre ProutièrePublished in: NeurIPS (2023)
Keyphrases
- model free
- active exploration
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- sequential decision problems
- state space
- temporal difference
- policy iteration
- reinforcement learning methods
- active learning
- machine learning
- learning algorithm
- markov decision processes
- optimal policy
- neural network
- optimal control
- problem based learning
- small sample
- temporal difference learning
- rl algorithms
- transfer learning
- higher education
- linear combination
- programming language
- learning process
- markov decision problems
- feature extraction
- real world