Expert Q-learning: Deep Q-learning With State Values From Expert Examples.
Li MengAnis YazidiMorten GoodwinPaal EngelstadPublished in: CoRR (2021)
Keyphrases
- state space
- cooperative
- reinforcement learning
- multi agent
- learning algorithm
- model free
- function approximation
- state action
- reinforcement learning algorithms
- expert knowledge
- stochastic approximation
- neural network
- domain experts
- state variables
- expert advice
- dynamic programming
- machine learning
- bucket brigade
- stochastic shortest path
- human experts
- markov decision processes
- optimal policy