8 citations · 38 across the 20 of their papers we have counts for
8 papers · 1 filter
Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Models
Alex Havrilla, Andrew Dai, Laura O'Mahony +17
Synthetic data generation with Large Language Models is a promising paradigm for augmenting natural data over a nearly infinite range of tasks. Given this variety, direct compariso…
Teaching Large Language Models to Reason with Reinforcement Learning
Alex Havrilla, Yuqing Du, Sharath Chandra Raparthy +6
Reinforcement Learning from Human Feedback (\textbf{RLHF}) has emerged as a dominant approach for aligning LLM outputs with human preferences. Inspired by the success of RLHF, we s…
Generalization to New Sequential Decision Making Tasks with In-Context Learning
Sharath Chandra Raparthy, Eric Hambro, Robert Kirk +2
Training autonomous agents that can learn new tasks from only a handful of demonstrations is a long-standing problem in machine learning. Recently, transformers have been shown to…
Multi-Objective GFlowNets
Moksh Jain, Sharath Chandra Raparthy, Alex Hernandez-Garcia +4
We study the problem of generating diverse candidates in the context of Multi-Objective Optimization. In many applications of machine learning such as drug discovery and material d…
Continual Learning In Environments With Polynomial Mixing Times
Matthew Riemer, Sharath Chandra Raparthy, Ignacio Cases +3
The mixing time of the Markov chain induced by a policy limits performance in real-world continual learning scenarios. Yet, the effect of mixing times on learning in continual rein…
Compositional Attention: Disentangling Search and Retrieval
Sarthak Mittal, Sharath Chandra Raparthy, Irina Rish +2
Multi-head, key-value attention is the backbone of the widely successful Transformer model and its variants. This attention mechanism uses multiple parallel key-value attention blo…
Curriculum in Gradient-Based Meta-Reinforcement Learning
Bhairav Mehta, Tristan Deleu, Sharath Chandra Raparthy +2
Gradient-based meta-learners such as Model-Agnostic Meta-Learning (MAML) have shown strong few-shot performance in supervised and reinforcement learning settings. However, specific…
Generating Automatic Curricula via Self-Supervised Active Domain Randomization
Sharath Chandra Raparthy, Bhairav Mehta, Florian Golemo +1
Goal-directed Reinforcement Learning (RL) traditionally considers an agent interacting with an environment, prescribing a real-valued reward to an agent proportional to the complet…