Mitigating Outlier Activations in Low-Precision Fine-Tuning of Language Models

no code implementations • 14 Dec 2023 • Alireza Ghaffari, Justin Yu, Mahsa Ghazvini Nejad, Masoud Asgharian, Boxing Chen, Vahid Partovi Nia

The benefit of using integers for outlier values is that it enables us to use operator tiling to avoid performing 16-bit integer matrix multiplication to address this problem effectively.

MURAL: Meta-Learning Uncertainty-Aware Rewards for Outcome-Driven Reinforcement Learning

no code implementations • 15 Jul 2021 • Kevin Li, Abhishek Gupta, Ashwin Reddy, Vitchyr Pong, Aurick Zhou, Justin Yu, Sergey Levine

In this work, we show that an uncertainty aware classifier can solve challenging reinforcement learning problems by both encouraging exploration and provided directed guidance towards positive outcomes.

Meta-Learning reinforcement-learning +1

Reset-Free Reinforcement Learning via Multi-Task Learning: Learning Dexterous Manipulation Behaviors without Human Intervention

no code implementations • 22 Apr 2021 • Abhishek Gupta, Justin Yu, Tony Z. Zhao, Vikash Kumar, Aaron Rovinsky, Kelvin Xu, Thomas Devlin, Sergey Levine

This work shows the ability to learn dexterous manipulation behaviors in the real world with RL without any human intervention.

Multi-Task Learning Reinforcement Learning (RL)

Reinforcement Learning with Bayesian Classifiers: Efficient Skill Learning from Outcome Examples

no code implementations • 1 Jan 2021 • Kevin Li, Abhishek Gupta, Vitchyr H. Pong, Ashwin Reddy, Aurick Zhou, Justin Yu, Sergey Levine

In this work, we study a more tractable class of reinforcement learning problems defined by data that provides examples of successful outcome states.

reinforcement-learning Reinforcement Learning (RL)

The Ingredients of Real World Robotic Reinforcement Learning

no code implementations • ICLR 2020 • Henry Zhu, Justin Yu, Abhishek Gupta, Dhruv Shah, Kristian Hartikainen, Avi Singh, Vikash Kumar, Sergey Levine

The success of reinforcement learning in the real world has been limited to instrumented laboratory scenarios, often requiring arduous human supervision to enable continuous learning.

reinforcement-learning Reinforcement Learning (RL)

The Ingredients of Real-World Robotic Reinforcement Learning

no code implementations • 27 Apr 2020 • Henry Zhu, Justin Yu, Abhishek Gupta, Dhruv Shah, Kristian Hartikainen, Avi Singh, Vikash Kumar, Sergey Levine

In this work, we discuss the elements that are needed for a robotic learning system that can continually and autonomously improve with data collected in the real world.

reinforcement-learning Reinforcement Learning (RL)