On the Generalization Gap in Reparameterizable Reinforcement Learning.
Huan WangStephan ZhengCaiming XiongRichard SocherPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- function approximation
- temporal difference
- reinforcement learning algorithms
- real world
- robotic control
- relational reinforcement learning
- reinforcement learning methods
- action selection
- state space
- multi agent
- training data
- learning algorithm
- database
- search algorithm
- supervised learning
- optimal policy
- radial basis function
- optimal control
- decision trees
- genetic algorithm
- machine learning