Search Results for author:
Found 3 papers, 3 papers with code
Disentangling Policy from Offline Task Representation Learning via Adversarial Data Augmentation
Specifically, the objective of adversarial data augmentation is not merely to generate data analogous to offline data distribution; instead, it aims to create adversarial examples designed to confound learned task representations and lead to incorrect task identification.
Generalizable Task Representation Learning for Offline Meta-Reinforcement Learning with Data Limitations
GENTLE employs Task Auto-Encoder~(TAE), which is an encoder-decoder architecture to extract the characteristics of the tasks.
ACT: Empowering Decision Transformer with Dynamic Programming via Advantage Conditioning
Third, we train an Advantage-Conditioned Transformer (ACT) to generate actions conditioned on the estimated advantages.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
