Balsa: Learning a Query Optimizer Without Expert Demonstrations

1 code implementation • 5 Jan 2022 • Zongheng Yang, Wei-Lin Chiang, Sifei Luan, Gautam Mittal, Michael Luo, Ion Stoica

Query optimizers are a performance-critical component in every database system.

MESA: Offline Meta-RL for Safe Adaptation and Fault Tolerance

no code implementations • 7 Dec 2021 • Michael Luo, Ashwin Balakrishna, Brijen Thananjeyan, Suraj Nair, Julian Ibarz, Jie Tan, Chelsea Finn, Ion Stoica, Ken Goldberg

Safe exploration is critical for using reinforcement learning (RL) in risk-sensitive environments.

Continuous Control Meta-Learning +2

Discovering Non-monotonic Autoregressive Orderings with Variational Inference

1 code implementation • 27 Oct 2021 • Xuanlin Li, Brandon Trabucco, Dong Huk Park, Michael Luo, Sheng Shen, Trevor Darrell, Yang Gao

Permutations then serve as target generation orders for training an insertion-based Transformer language model.

Image Captioning Language Modelling +3

Accelerating Quadratic Optimization with Reinforcement Learning

1 code implementation • NeurIPS 2021 • Jeffrey Ichnowski, Paras Jain, Bartolomeo Stellato, Goran Banjac, Michael Luo, Francesco Borrelli, Joseph E. Gonzalez, Ion Stoica, Ken Goldberg

First-order methods for quadratic optimization such as OSQP are widely used for large-scale machine learning and embedded optimal control, where many related problems must be rapidly solved.

reinforcement-learning Reinforcement Learning (RL)

LazyDAgger: Reducing Context Switching in Interactive Imitation Learning

no code implementations • 31 Mar 2021 • Ryan Hoque, Ashwin Balakrishna, Carl Putterman, Michael Luo, Daniel S. Brown, Daniel Seita, Brijen Thananjeyan, Ellen Novoseller, Ken Goldberg

Corrective interventions while a robot is learning to automate a task provide an intuitive method for a human supervisor to assist the robot and convey information about desired behavior.

Continuous Control Imitation Learning

Discovering Autoregressive Orderings with Variational Inference

1 code implementation • ICLR 2021 • Xuanlin Li, Brandon Trabucco, Dong Huk Park, Michael Luo, Sheng Shen, Trevor Darrell, Yang Gao

One strategy to recover this information is to decode both the content and location of tokens.

Code Generation Image Captioning +2

Connecting Context-specific Adaptation in Humans to Meta-learning

no code implementations • 27 Nov 2020 • Rachit Dubey, Erin Grant, Michael Luo, Karthik Narasimhan, Thomas Griffiths

This work connects the context-sensitive nature of cognitive control to a method for meta-learning with context-conditioned adaptation.

Meta-Learning

RLlib Flow: Distributed Reinforcement Learning is a Dataflow Problem

1 code implementation • NeurIPS 2021 • Eric Liang, Zhanghao Wu, Michael Luo, Sven Mika, Joseph E. Gonzalez, Ion Stoica

Researchers and practitioners in the field of reinforcement learning (RL) frequently leverage parallel computation, which has led to a plethora of new algorithms and systems in the last few years.

reinforcement-learning Reinforcement Learning (RL)

Recovery RL: Safe Reinforcement Learning with Learned Recovery Zones

2 code implementations • 29 Oct 2020 • Brijen Thananjeyan, Ashwin Balakrishna, Suraj Nair, Michael Luo, Krishnan Srinivasan, Minho Hwang, Joseph E. Gonzalez, Julian Ibarz, Chelsea Finn, Ken Goldberg

Safety remains a central obstacle preventing widespread use of RL in the real world: learning new tasks in uncertain environments requires extensive exploration, but safety requires limiting exploration.

reinforcement-learning Reinforcement Learning (RL) +1

IMPACT: Importance Weighted Asynchronous Architectures with Clipped Target Networks

no code implementations • ICLR 2020 • Michael Luo, Jiahao Yao, Richard Liaw, Eric Liang, Ion Stoica

To address this, we propose a new distributed reinforcement learning algorithm, IMPACT.

Continuous Control reinforcement-learning +1