Research on task decomposition and state abstraction in reinforcement learning.
Lasheng YuZhongbin JiangKang LiuPublished in: Artif. Intell. Rev. (2012)
Keyphrases
- state abstraction
- reinforcement learning
- state space
- hierarchical reinforcement learning
- reinforcement learning agents
- markov decision processes
- reinforcement learning algorithms
- path finding
- function approximation
- multi agent
- initial state
- optimal policy
- learning algorithm
- hierarchical decomposition
- model free
- optimal control
- machine learning
- supervised learning
- transfer learning
- infinite horizon
- markov chain
- partially observable
- action space
- dynamic environments
- search algorithm
- shortest path