Assessing Generalization in Deep Reinforcement Learning.
Charles PackerKatelyn GaoJernej KosPhilipp KrähenbühlVladlen KoltunDawn SongPublished in: CoRR (2018)
Keyphrases
- reinforcement learning
- markov decision processes
- state space
- temporal difference
- reinforcement learning algorithms
- databases
- learning problems
- transfer learning
- optimal policy
- control problems
- dynamic programming
- learning process
- feature selection
- artificial intelligence
- multi agent reinforcement learning
- partially observable
- relational reinforcement learning
- robotic control
- model free
- learning classifier systems
- function approximation
- unsupervised learning
- supervised learning
- learning algorithm
- neural network