PDT jointly learns an embedding space of future trajectory as well as a future prior conditioned only on past information.. By conditioning action prediction on the target future embedding, PDT is endowed with the ability to "reason over the future". This ability is naturally task-independent and can be generalized to different task specifications. To achieve efficient online fine-tuning in downstream tasks, you can easily adapt the framework to new conditions by associating each ...
Go to Profile
Mark as Read
