Randomized Prior Functions for Deep Reinforcement Learning.
Ian OsbandJohn AslanidesAlbin CassirerPublished in: CoRR (2018)
Keyphrases
- reinforcement learning
- data sets
- machine learning
- prior knowledge
- neural network
- database
- optimal policy
- markov decision processes
- function approximation
- policy search
- transition model
- reinforcement learning methods
- temporal difference learning
- optimal control
- state space
- multi agent
- knowledge base
- artificial intelligence