The factored policy-gradient planner.
Olivier BuffetDouglas AberdeenPublished in: Artif. Intell. (2009)
Keyphrases
- policy gradient
- actor critic
- reinforcement learning
- parametric optimization
- state space
- reinforcement learning algorithms
- heuristic search
- function approximation
- gradient method
- optimal control
- approximation methods
- model free reinforcement learning
- variance reduction
- average reward
- machine learning
- domain independent
- reinforcement learning methods
- initial state