Search Results - "Song, Xingyou"

Automated Reinforcement Learning (AutoRL): A Survey and Open Problems by Parker-Holder, Jack, Rajan, Raghu, Song, Xingyou, Biedenkapp, André, Miao, Yingjie, Eimer, Theresa, Zhang, Baohe, Nguyen, Vu, Calandra, Roberto, Faust, Aleksandra, Hutter, Frank, Lindauer, Marius

“…The combination of Reinforcement Learning (RL) with deep learning has led to a series of impressive feats, with many believing (deep) RL provides a path…”
Get full text

Optimization of English Language and Literature Teaching Management System Based on Artificial Intelligence and Computer-Aided Design by Gu, Shan, Song, Xingyou, Wu, Lei

Get full text

Rapidly Adaptable Legged Robots via Evolutionary Meta-Learning by Song, Xingyou, Yang, Yuxiang, Choromanski, Krzysztof, Caluwaerts, Ken, Gao, Wenbo, Finn, Chelsea, Tan, Jie

“…Learning adaptable policies is crucial for robots to operate autonomously in our complex and quickly changing world. In this work, we present a new…”
Get full text

Robotic Table Tennis with Model-Free Reinforcement Learning by Gao, Wenbo, Graesser, Laura, Choromanski, Krzysztof, Song, Xingyou, Lazic, Nevena, Sanketi, Pannag, Sindhwani, Vikas, Jaitly, Navdeep

“…We propose a model-free algorithm for learning efficient policies capable of returning table tennis balls by controlling robot joints at a rate of 100Hz. We…”
Get full text

Discovering Adaptable Symbolic Algorithms from Scratch by Kelly, Stephen, Park, Daniel S., Song, Xingyou, McIntire, Mitchell, Nashikkar, Pranav, Guha, Ritam, Banzhaf, Wolfgang, Deb, Kalyanmoy, Boddeti, Vishnu Naresh, Tan, Jie, Real, Esteban

“…Autonomous robots deployed in the real world will need control policies that rapidly adapt to environmental changes. To this end, we propose AutoRobotics-Zero…”
Get full text

Quantum Cellular Automata Models for General Dirac Equation by Song, Xingyou

“…The goal of this study is to provide an exact unitary quantum cellular automata that, under discrete time steps, converges towards the Generalized Dirac…”
Get full text

The Principle of Unchanged Optimality in Reinforcement Learning Generalization by Irpan, Alex, Song, Xingyou

“…Several recent papers have examined generalization in reinforcement learning (RL), by proposing new environments or ways to add noise to existing environments,…”
Get full text

Hardness of Low Rank Approximation of Entrywise Transformed Matrix Products by Sarlos, Tamas, Song, Xingyou, Woodruff, David, Qiuyi, Zhang

“…Inspired by fast algorithms in natural language processing, we study low rank approximation in the entrywise transformed setting where we want to find a good…”
Get full text

Position: Leverage Foundational Models for Black-Box Optimization by Song, Xingyou, Tian, Yingtao, Lange, Robert Tjarko, Lee, Chansoo, Tang, Yujin, Chen, Yutian

“…Undeniably, Large Language Models (LLMs) have stirred an extraordinary wave of innovation in the machine learning research domain, resulting in substantial…”
Get full text

Open Source Vizier: Distributed Infrastructure and API for Reliable and Flexible Blackbox Optimization by Song, Xingyou, Perel, Sagi, Lee, Chansoo, Kochanski, Greg, Golovin, Daniel

“…Vizier is the de-facto blackbox and hyperparameter optimization service across Google, having optimized some of Google's largest products and research efforts…”
Get full text

OmniPred: Language Models as Universal Regressors by Song, Xingyou, Li, Oscar, Lee, Chansoo, Yang, Bangding, Peng, Daiyi, Perel, Sagi, Chen, Yutian

“…Over the broad landscape of experimental design, regression has been a powerful tool to accurately predict the outcome metrics of a system or model given a set…”
Get full text

Predicting from Strings: Language Model Embeddings for Bayesian Optimization by Nguyen, Tung, Zhang, Qiuyi, Yang, Bangding, Lee, Chansoo, Bornschein, Jorg, Miao, Yingjie, Perel, Sagi, Chen, Yutian, Song, Xingyou

“…Bayesian Optimization is ubiquitous in the field of experimental design and blackbox optimization for improving search efficiency, but has been traditionally…”
Get full text

Debiasing a First-order Heuristic for Approximate Bi-level Optimization by Likhosherstov, Valerii, Song, Xingyou, Choromanski, Krzysztof, Davis, Jared, Weller, Adrian

“…Approximate bi-level optimization (ABLO) consists of (outer-level) optimization problems, involving numerical (inner-level) optimization loops. While ABLO has…”
Get full text

The Vizier Gaussian Process Bandit Algorithm by Song, Xingyou, Zhang, Qiuyi, Lee, Chansoo, Fertig, Emily, Huang, Tzu-Kuo, Belenki, Lior, Kochanski, Greg, Ariafar, Setareh, Vasudevan, Srinivas, Perel, Sagi, Golovin, Daniel

“…Google Vizier has performed millions of optimizations and accelerated numerous research and production systems at Google, demonstrating the success of Bayesian…”
Get full text

An Empirical Study on Hyperparameters and their Interdependence for RL Generalization by Song, Xingyou, Du, Yilun, Jackson, Jacob

“…Recent results in Reinforcement Learning (RL) have shown that agents with limited training environments are susceptible to a large amount of overfitting across…”
Get full text

Sub-Linear Memory: How to Make Performers SLiM by Likhosherstov, Valerii, Choromanski, Krzysztof, Davis, Jared, Song, Xingyou, Weller, Adrian

“…The Transformer architecture has revolutionized deep learning on sequential data, becoming ubiquitous in state-of-the-art solutions for a wide variety of…”
Get full text

UFO-BLO: Unbiased First-Order Bilevel Optimization by Likhosherstov, Valerii, Song, Xingyou, Choromanski, Krzysztof, Davis, Jared, Weller, Adrian

“…Bilevel optimization (BLO) is a popular approach with many applications including hyperparameter optimization, neural architecture search, adversarial…”
Get full text

Discovering Adaptable Symbolic Algorithms from Scratch by Kelly, Stephen, Park, Daniel S, Song, Xingyou, McIntire, Mitchell, Nashikkar, Pranav, Guha, Ritam, Banzhaf, Wolfgang, Deb, Kalyanmoy, Boddeti, Vishnu Naresh, Tan, Jie, Real, Esteban

“…Autonomous robots deployed in the real world will need control policies that rapidly adapt to environmental changes. To this end, we propose AutoRobotics-Zero…”
Get full text

Observational Overfitting in Reinforcement Learning by Song, Xingyou, Jiang, Yiding, Tu, Stephen, Du, Yilun, Neyshabur, Behnam

“…A major component of overfitting in model-free reinforcement learning (RL) involves the case where the agent may mistakenly correlate reward with certain…”
Get full text

Differentiable Architecture Search for Reinforcement Learning by Miao, Yingjie, Song, Xingyou, Co-Reyes, John D, Peng, Daiyi, Yue, Summer, Brevdo, Eugene, Faust, Aleksandra

“…In this paper, we investigate the fundamental question: To what extent are gradient-based neural architecture search (NAS) techniques applicable to RL? Using…”
Get full text