2 papers
cs.CL2024
The Synergy of LLMs & RL Unlocks Offline Learning of Generalizable Language-Conditioned Policies with Low-fidelity Data
Thomas Pouplin, Katarzyna Kobalczyk, Hao Sun +1
Developing autonomous agents capable of performing complex, multi-step decision-making tasks specified in natural language remains a significant challenge, particularly in realisti…
cs.LG2024
Towards Automated Knowledge Integration From Human-Interpretable Representations
Katarzyna Kobalczyk, Mihaela van der Schaar
A significant challenge in machine learning, particularly in noisy and low-data environments, lies in effectively incorporating inductive biases to enhance data efficiency and robu…