REFACTOR: Learning to Extract Theorems from Proofs

1 code implementation • 26 Feb 2024 • Jin Peng Zhou, Yuhuai Wu, Qiyang Li, Roger Grosse

With newly extracted theorems, we show that the existing proofs in the MetaMath database can be refactored.

Automated Theorem Proving

Accelerating Exploration with Unlabeled Prior Data

1 code implementation • NeurIPS 2023 • Qiyang Li, Jason Zhang, Dibya Ghosh, Amy Zhang, Sergey Levine

Learning to solve tasks from a sparse reward signal is a major challenge for standard reinforcement learning (RL) algorithms.

Reinforcement Learning (RL)

Efficient Deep Reinforcement Learning Requires Regulating Overfitting

no code implementations • 20 Apr 2023 • Qiyang Li, Aviral Kumar, Ilya Kostrikov, Sergey Levine

Deep reinforcement learning algorithms that learn policies by trial-and-error must learn from limited amounts of data collected by actively interacting with the environment.

Model Selection reinforcement-learning

Understanding the Complexity Gains of Single-Task RL with a Curriculum

no code implementations • 24 Dec 2022 • Qiyang Li, Yuexiang Zhai, Yi Ma, Sergey Levine

Under mild regularity conditions on the curriculum, we show that sequentially solving each task in the multi-task RL problem is more computationally efficient than solving the original single-task problem, without any explicit exploration bonuses or other exploration strategies.

Reinforcement Learning (RL)

AdaCat: Adaptive Categorical Discretization for Autoregressive Models

1 code implementation • 3 Aug 2022 • Qiyang Li, Ajay Jain, Pieter Abbeel

Autoregressive generative models can estimate complex continuous data distributions, like trajectory rollouts in an RL environment, image intensities, and audio.

Density Estimation Offline RL

Reinforcement Learning as One Big Sequence Modeling Problem

1 code implementation • ICML Workshop URL 2021 • Michael Janner, Qiyang Li, Sergey Levine

However, we can also view RL as a sequence modeling problem, with the goal being to predict a sequence of actions that leads to a sequence of high rewards.

Imitation Learning Offline RL +2

Offline Reinforcement Learning as One Big Sequence Modeling Problem

2 code implementations • NeurIPS 2021 • Michael Janner, Qiyang Li, Sergey Levine

Reinforcement learning (RL) is typically concerned with estimating stationary policies or single-step models, leveraging the Markov property to factorize problems in time.

Imitation Learning Offline RL +2

R-LAtte: Attention Module for Visual Control via Reinforcement Learning

no code implementations • 1 Jan 2021 • Mandi Zhao, Qiyang Li, Aravind Srinivas, Ignasi Clavera, Kimin Lee, Pieter Abbeel

Attention mechanisms are generic inductive biases that have played a critical role in improving the state-of-the-art in supervised learning, unsupervised pre-training and generative modeling for multiple domains including vision, language and speech.

reinforcement-learning Reinforcement Learning (RL) +1

Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks

1 code implementation • NeurIPS 2019 • Qiyang Li, Saminul Haque, Cem Anil, James Lucas, Roger Grosse, Jörn-Henrik Jacobsen

Our BCOP parameterization allows us to train large convolutional networks with provable Lipschitz bounds.

Adversarial Robustness

TimbreTron: A WaveNet(CycleGAN(CQT(Audio))) Pipeline for Musical Timbre Transfer

1 code implementation • ICLR 2019 • Sicong Huang, Qiyang Li, Cem Anil, Xuchan Bao, Sageev Oore, Roger B. Grosse

In this work, we address the problem of musical timbre transfer, where the goal is to manipulate the timbre of a sound sample from one instrument to match another instrument while preserving other musical content, such as pitch, rhythm, and loudness.

Style Transfer

Building a Winning Self-Driving Car in Six Months

no code implementations • 3 Nov 2018 • Keenan Burnett, Andreas Schimpe, Sepehr Samavi, Mona Gridseth, Chengzhi Winston Liu, Qiyang Li, Zachary Kroeze, Angela P. Schoellig

The first set of challenges were held in April of 2018 in Yuma, Arizona.

Robotics

Learning of Coordination Policies for Robotic Swarms

no code implementations • 19 Sep 2017 • Qiyang Li, Xintong Du, Yizhou Huang, Quinlan Sykora, Angela P. Schoellig

Inspired by biological swarms, robotic swarms are envisioned to solve real-world problems that are difficult for individual agents.

Deep Neural Networks for Improved, Impromptu Trajectory Tracking of Quadrotors

no code implementations • 20 Oct 2016 • Qiyang Li, Jingxing Qian, Zining Zhu, Xuchan Bao, Mohamed K. Helwa, Angela P. Schoellig

Trajectory tracking control for quadrotors is important for applications ranging from surveying and inspection, to film making.

Unity