Reinforcement learning with convolutional reservoir computing.
Hanten ChangKatsuya FutagamiPublished in: Appl. Intell. (2020)
Keyphrases
- reservoir computing
- reinforcement learning
- recurrent neural networks
- function approximation
- state space
- sparse coding
- neural network
- optimal control
- robotic control
- learning agents
- optimal policy
- multi agent reinforcement learning
- learning algorithm
- network architecture
- model free
- deep learning
- control problems
- reinforcement learning algorithms
- markov decision processes
- learning process
- transition model
- information systems
- real world
- real robot
- temporal difference
- action selection
- back propagation
- dynamic programming
- multi agent