Efficient Stagewise Pretraining via Progressive Subnetworks

no code implementations • 8 Feb 2024 • Abhishek Panigrahi, Nikunj Saunshi, Kaifeng Lyu, Sobhan Miryoosefi, Sashank Reddi, Satyen Kale, Sanjiv Kumar

RaPTr achieves better pre-training loss for BERT and UL2 language models while requiring 20-33% fewer FLOPs compared to standard training, and is competitive or better than other efficient training methods.

ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent

no code implementations • 15 Dec 2023 • Renat Aksitov, Sobhan Miryoosefi, Zonglin Li, Daliang Li, Sheila Babayan, Kavya Kopparapu, Zachary Fisher, Ruiqi Guo, Sushant Prakash, Pranesh Srinivasan, Manzil Zaheer, Felix Yu, Sanjiv Kumar

Answering complex natural language questions often necessitates multi-step reasoning and integrating external information.

Language Modelling Large Language Model +2

Provable Reinforcement Learning with a Short-Term Memory

no code implementations • 8 Feb 2022 • Yonathan Efroni, Chi Jin, Akshay Krishnamurthy, Sobhan Miryoosefi

Real-world sequential decision making problems commonly involve partial observability, which requires the agent to maintain a memory of history in order to infer the latent states, plan and make good decisions.

Decision Making reinforcement-learning +1

A Simple Reward-free Approach to Constrained Reinforcement Learning

no code implementations • 12 Jul 2021 • Sobhan Miryoosefi, Chi Jin

In constrained reinforcement learning (RL), a learning agent seeks to not only optimize the overall reward but also satisfy the additional safety, diversity, or budget constraints.

reinforcement-learning Reinforcement Learning (RL)

Bellman Eluder Dimension: New Rich Classes of RL Problems, and Sample-Efficient Algorithms

no code implementations • NeurIPS 2021 • Chi Jin, Qinghua Liu, Sobhan Miryoosefi

Finding the minimal structural assumptions that empower sample-efficient learning is one of the most important research directions in Reinforcement Learning (RL).

Reinforcement Learning (RL)

Constrained episodic reinforcement learning in concave-convex and knapsack settings

1 code implementation • NeurIPS 2020 • Kianté Brantley, Miroslav Dudik, Thodoris Lykouris, Sobhan Miryoosefi, Max Simchowitz, Aleksandrs Slivkins, Wen Sun

We propose an algorithm for tabular episodic reinforcement learning with constraints.

reinforcement-learning Reinforcement Learning (RL)

Reinforcement Learning with Convex Constraints

1 code implementation • NeurIPS 2019 • Sobhan Miryoosefi, Kianté Brantley, Hal Daumé III, Miroslav Dudik, Robert Schapire

In standard reinforcement learning (RL), a learning agent seeks to optimize the overall reward.

reinforcement-learning Reinforcement Learning (RL)