Faster Reinforcement Learning Using Active Simulators.
Vikas JainTheja TulabandhulaPublished in: CoRR (2017)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- reinforcement learning methods
- control problems
- dynamic programming
- optimal policy
- robotic control
- real time
- memory efficient
- robot control
- optimal control
- temporal difference
- state space
- search algorithm
- case study
- information systems
- social networks
- relational reinforcement learning
- data sets