A Neuromorphic Architecture for Reinforcement Learning from Real-Valued Observations.
Sérgio F. ChevtchenkoYeshwanth BethiTeresa Bernarda LudermirSaeed AfsharPublished in: CoRR (2023)
Keyphrases
- real valued
- reinforcement learning
- action space
- complex valued
- integer valued
- interval valued
- real valued data
- learning algorithm
- continuous functions
- latent variables
- multiple instance
- feature selection
- markov decision processes
- prior knowledge
- support vector
- low variance
- distributed representations
- information retrieval