TD-VAE, or Temporal Difference VAE, is a generative sequence model that learns representations containing explicit beliefs about states several steps into the future, and that can be rolled out directly without single-step transitions. TD-VAE is trained on pairs of temporally separated time points, using an analogue of temporal difference learning used in reinforcement learning.
Source: Temporal Difference Variational Auto-EncoderPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Story Generation | 1 | 33.33% |
Text Generation | 1 | 33.33% |
Reinforcement Learning (RL) | 1 | 33.33% |