Photonic reinforcement learning based on optoelectronic reservoir computing.
Kazutaka KannoAtsushi UchidaPublished in: CoRR (2022)
Keyphrases
- reservoir computing
- reinforcement learning
- recurrent neural networks
- function approximation
- reinforcement learning algorithms
- state space
- physical characteristics
- multi agent
- learning algorithm
- model free
- case study
- markov decision processes
- machine learning
- feed forward
- temporal difference learning
- multi agent reinforcement learning
- database
- reinforcement learning methods