Towards More Sample Efficiency in Reinforcement Learning with Data Augmentation.
Yijiong LinJiancong HuangMatthieu ZimmerJuan RojasPaul WengPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- data collection
- high quality
- statistical analysis
- data sets
- experimental data
- sensor data
- data processing
- data analysis
- data samples
- knowledge discovery
- data points
- data structure
- end users
- complex data
- small number
- input data
- training set
- data quality
- noisy data
- raw data
- database
- data sources
- markov decision processes
- test data
- data distribution
- neural network
- microarray
- database systems
- high dimensional data
- multi agent
- xml documents
- prior knowledge