Instance-based Generalization in Reinforcement Learning.
Martín BertránNatalia MartínezMariano PhielippGuillermo SapiroPublished in: NeurIPS (2020)
Keyphrases
- reinforcement learning
- model free
- function approximation
- learning algorithm
- temporal difference
- markov decision processes
- instance based learning
- reinforcement learning algorithms
- knn
- policy search
- real world
- learning capabilities
- optimal policy
- supervised learning
- state space
- dynamic programming
- partially observable
- markov decision process
- search space
- learning agent
- machine learning