MULTIPOLAR: Multi-Source Policy Aggregation for Transfer Reinforcement Learning between Diverse Environmental Dynamics.
Mohammadamin BarekatainRyo YonetaniMasashi HamayaPublished in: IJCAI (2020)
Keyphrases
- social network analysis
- multi source
- reinforcement learning
- optimal policy
- policy search
- data fusion
- information fusion
- transfer learning
- action selection
- markov decision process
- single source
- markov decision processes
- multiple sources
- function approximation
- reward function
- action space
- soft clustering
- data integration
- function approximators
- policy gradient
- multiple data sources
- dynamical systems
- state space
- data sources
- information integration
- databases
- multi attribute
- data sets
- supervised learning
- machine learning
- neural network
- decision support
- reinforcement learning algorithms
- database systems
- genetic algorithm
- data mining
- real world