Improving Batch Reinforcement Learning Performance through Transfer of Samples.
Alessandro LazaricMarcello RestelliAndrea BonariniPublished in: STAIRS (2008)
Keyphrases
- reinforcement learning
- transfer learning
- decision trees
- function approximation
- model free
- multi agent
- knowledge transfer
- state space
- optimal policy
- data sets
- multi agent reinforcement learning
- batch processing
- batch mode
- temporal difference
- markov decision processes
- training samples
- monte carlo
- training set
- training data
- case study
- machine learning
- neural network
- database
- robotic control