Model-Free Active Exploration in Reinforcement Learning.
Alessio RussoAlexandre ProutièrePublished in: CoRR (2024)
Keyphrases
- model free
- active exploration
- reinforcement learning
- reinforcement learning algorithms
- sequential decision problems
- function approximation
- state space
- temporal difference
- machine learning
- policy iteration
- active learning
- reinforcement learning methods
- rl algorithms
- learning algorithm
- optimal policy
- markov decision processes
- decision problems
- learning problems
- dynamic programming
- small sample
- average reward