Universal Successor Representations for Transfer Reinforcement Learning.
Chen MaJunfeng WenYoshua BengioPublished in: CoRR (2018)
Keyphrases
- reinforcement learning
- transfer learning
- function approximation
- sequence prediction
- model free
- state space
- multi agent
- temporal difference
- multiple representations
- higher level
- optimal policy
- bayesian networks
- autonomous learning
- learning process
- markov decision processes
- optimal control
- database
- function approximators
- learning capabilities
- reinforcement learning algorithms
- action selection
- neural network
- symbolic representation
- machine learning
- genetic algorithm
- learning algorithm
- learning environment
- decision trees