Reinforcement Learning
How to Solve Contextual Goal-Oriented Problems with Offline Datasets?
We conduct a novel theoretical analysis to demonstrate CODA's
Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards
Project lead, main contributor, correspondence to alexandre.rame@isir.upmc.fr. Equal experimental contribution, order determined at random. Further information and resources related to this project can be found on this website.
Entropy-regularized Diffusion Policy with Q-Ensembles for Offline Reinforcement Learning
Left: The reward function is a mixture of Gaussian, and the offline data distribution is unbalanced with most samples located in low-reward states.
Diffusion-DICE: In-Sample Diffusion Guidance for Offline Reinforcement Learning Liyuan Mao Shanghai Jiao Tong University Haoran Xu UT Austin Xianyuan Zhan Tsinghua University Weinan Zhang
Based on this, we propose a novel approach, Diffusion-DICE, that directly performs this transformation using diffusion models.
Extracting Training Data from Molecular Pre-trained Models
This work, for the first time, explores the risks of extracting private training molecular data from molecular pre-trained models. This task is nontrivial as the molecular pre-trained models are non-generative and exhibit a diversity of model architectures, which differs significantly from language and image models.
Diffusion-based Curriculum Reinforcement Learning
V arious approaches have been proposed for the generation of curriculum goals.
OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensembling
In such cases, re-training the model from scratch could be time-consuming.
dd03f856fc7f2efeec8b1c796284561d-Paper-Conference.pdf
Short-horizon tasks require few steps: e.g., go to a tree and chop it down, dig a hole.