Offline reinforcement learning with task hierarchies.
Devin SchwabSoumya RayPublished in: Mach. Learn. (2017)
Keyphrases
- reinforcement learning
- state space
- function approximation
- real time
- learning algorithm
- optimal policy
- machine learning
- temporal difference
- robotic control
- multi agent reinforcement learning
- function approximators
- reinforcement learning algorithms
- hierarchical structure
- direct policy search
- reinforcement learning methods
- model free
- optimal control
- dynamic programming
- information systems
- partially observable
- control problems
- support vector
- information retrieval
- policy search
- data mining
- neural network