← Search

Jikun Kang

2 accepted papers

2024

Think Before You Act: Decision Transformers with Working Memory

ICML 2024poster

Decision Transformer-based decision-making agents have shown the ability to generalize across multiple tasks. However, their performance relies on massive data and computation. We argue that this inefficiency stems from the forgetting phenomenon, in which a model memorizes its behaviors in parameter…

2022

Learning Multi-Objective Curricula for Robotic Policy Learning

CoRL 2022poster

Various automatic curriculum learning (ACL) methods have been proposed to improve the sample efficiency and final performance of robots' policies learning. They are designed to control how a robotic agent collects data, which is inspired by how humans gradually adapt their learning processes to thei…

Cited by 4SourcecodeScholar