Super-polynomial separations for quantum-enhanced reinforcement learning.
Vedran DunjkoYi-Kai LiuXingyao WuJacob M. TaylorPublished in: CoRR (2017)
Keyphrases
- reinforcement learning
- function approximation
- machine learning
- optimal policy
- quantum computation
- temporal difference
- action selection
- transfer learning
- multi agent
- decision trees
- function approximators
- multi agent reinforcement learning
- quantum computing
- learning process
- low power
- learning algorithm
- reinforcement learning algorithms
- policy search
- database