A Brief Survey of Deep Reinforcement Learning.
Kai ArulkumaranMarc Peter DeisenrothMiles BrundageAnil Anthony BharathPublished in: CoRR (2017)
Keyphrases
- reinforcement learning
- function approximation
- machine learning
- optimal policy
- state space
- neural network
- multi agent reinforcement learning
- control problems
- information systems
- data collection
- robotic control
- real time
- deep learning
- reinforcement learning algorithms
- temporal difference
- model free
- artificial intelligence
- learning algorithm
- real world
- learning problems
- markov decision processes
- supervised learning
- learning process
- partially observable
- action space
- temporal difference learning
- information retrieval
- policy search