8 papers
Test-Time Scaling via Error Localization
Rajiv Shailesh Chitale, Rahul Madhavan, Taneesh Gupta +2
Scaling inference-time computation has emerged as a reliable method to improve the performance of large language models on complex reasoning and programming tasks. However, standar…
Dense and Diverse Goal Coverage in Multi Goal Reinforcement Learning
Sagalpreet Singh, Rishi Saket, Aravindan Raghuveer
Reinforcement Learning algorithms are primarily focused on learning a policy that maximizes expected return. As a result, the learned policy can exploit one or few reward sources.…
Algorithmic Guarantees for Distilling Supervised and Offline RL Datasets
Aaryan Gupta, Rishi Saket, Aravindan Raghuveer
Given a training dataset, the goal of dataset distillation is to derive a synthetic dataset such that models trained on the latter perform as well as those trained on the training…
Preserving Expert-Level Privacy in Offline Reinforcement Learning
Navodita Sharma, Vishnu Vinod, Abhradeep Thakurta +4
The offline reinforcement learning (RL) problem aims to learn an optimal policy from historical data collected by one or more behavioural policies (experts) by interacting with an…
A Personalized Exercise Assistant using Reinforcement Learning (PEARL): Results from a four-arm Randomized-controlled Trial
Amy Armento Lee, Narayan Hegde, Nina Deliu +16
Consistent physical inactivity poses a major global health challenge. Mobile health (mHealth) interventions, particularly Just-in-Time Adaptive Interventions (JITAIs), offer a prom…
Learning from Label Proportions and Covariate-shifted Instances
Sagalpreet Singh, Navodita Sharma, Shreyas Havaldar +2
In many applications, especially due to lack of supervision or privacy concerns, the training data is grouped into bags of instances (feature-vectors) and for each bag we have only…