Meta-Q-Learning.
Rasool FakoorPratik ChaudhariStefano SoattoAlexander J. SmolaPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- cooperative
- function approximation
- multi agent
- learning algorithm
- state space
- meta level
- learning rate
- reinforcement learning algorithms
- potential field
- stochastic approximation
- action selection
- model free
- optimal policy
- real world
- reinforcement learning methods
- information systems
- database
- radial basis function
- markov chain
- evolutionary algorithm
- case study
- social networks
- relational reinforcement learning
- bucket brigade