Meta-Q-Learning.
Rasool FakoorPratik ChaudhariStefano SoattoAlexander J. SmolaPublished in: ICLR (2020)
Keyphrases
- reinforcement learning
- cooperative
- function approximation
- multi agent
- learning algorithm
- model free
- state space
- stochastic approximation
- optimal policy
- temporal difference learning
- action selection
- meta level
- dynamic programming
- genetic algorithm
- meta reasoning
- learning rate
- dynamic environments
- markov chain
- domain knowledge
- case study
- multi agent reinforcement learning
- information retrieval