Simultaneous Abstract and Concrete Reinforcement Learning.
Tiago MatosYannick Plaino BergamoValdinei Freire da SilvaFábio Gagliardi CozmanAnna Helena Reali CostaPublished in: SARA (2011)
Keyphrases
- reinforcement learning
- function approximation
- robotic control
- model free
- reinforcement learning algorithms
- high level
- state space
- multi agent
- markov decision processes
- higher level
- dynamic programming
- temporal difference
- learning problems
- optimal policy
- supervised learning
- machine learning
- database
- low level
- learning process
- search algorithm
- learning environment
- case study
- information retrieval
- data mining
- markov decision process
- temporal difference learning
- data sets