1 code implementation • 20 Jan 2024 • Raj Ghugare, Matthieu Geist, Glen Berseth, Benjamin Eysenbach
Based on this analysis, we construct new datasets to explicitly test for this property, revealing that SL-based methods lack this stitching property and hence fail to perform combinatorial generalization.
no code implementations • 4 Oct 2023 • Raj Ghugare, Santiago Miret, Adriana Hugessen, Mariano Phielipp, Glen Berseth
Reinforcement learning (RL) over text representations can be effective for finding high-value policies that can search over graphs.
no code implementations • 18 Sep 2022 • Raj Ghugare, Homanga Bharadhwaj, Benjamin Eysenbach, Sergey Levine, Ruslan Salakhutdinov
In this work, we propose a single objective which jointly optimizes a latent-space model and policy to achieve high returns while remaining self-consistent.