The Value-Improvement Path: Towards Better Representations for Reinforcement Learning.
Will DabneyAndré BarretoMark RowlandRobert DadashiJohn QuanMarc G. BellemareDavid SilverPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- higher level
- shortest path
- function approximation
- temporal difference learning
- learning algorithm
- multi agent reinforcement learning
- function approximators
- significant improvement
- reinforcement learning algorithms
- robotic control
- policy search
- temporal difference
- markov decision processes
- dynamical systems
- state space
- dynamic programming
- relational databases
- multi agent
- bayesian networks
- social networks
- search engine