Episodic Reinforcement Learning with Associative Memory.
Guangxiang ZhuZichuan LinGuangwen YangChongjie ZhangPublished in: ICLR (2020)
Keyphrases
- associative memory
- reinforcement learning
- storage capacity
- kohonen feature map
- bi directional
- function approximation
- alpha beta
- state space
- markov decision processes
- auto associative
- machine learning
- learning process
- human memory
- learning algorithm
- neural network
- reinforcement learning algorithms
- model free
- data sets
- action space
- learning capabilities
- temporal difference
- complex systems
- action selection
- data mining
- image processing
- optimal control
- neural network model
- kernel methods
- feature space