Search Results for author:
Found 3 papers, 2 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.
Policy Regularization with Dataset Constraint for Offline Reinforcement Learning
A common taxonomy of existing offline RL works is policy regularization, which typically constrains the learned policy by distribution or support of the behavior policy.
Multi-agent Continual Coordination via Progressive Task Contextualization
Towards tackling the mentioned issue, this paper proposes an approach Multi-Agent Continual Coordination via Progressive Task Contextualization, dubbed MACPro.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
