All current TVO models refer to the "decoder" part of classical variational autoencoders. Current work, such as the neural state proposer uses model-based learning.
Proposed changes:
Make the Trainable protocol an abstraction of two new Encoder and Decoder protocols.
Enable gradient-based state acquisition in TrainingAndOrValidation.
All current TVO models refer to the "decoder" part of classical variational autoencoders. Current work, such as the neural state proposer uses model-based learning.
Proposed changes:
Make the Trainable protocol an abstraction of two new Encoder and Decoder protocols.
Enable gradient-based state acquisition in TrainingAndOrValidation.