Bob McGrew — accepted AI-conference papers

2022

GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models

Alexander Quinn Nichol, Prafulla Dhariwal, Aditya Ramesh, Pranav Shyam, Pamela Mishkin, Bob Mcgrew +2

ICML 2022spotlight

Diffusion models have recently been shown to generate high-quality synthetic images, especially when paired with a guidance technique to trade off diversity for fidelity. We explore diffusion models for the problem of text-conditional image synthesis and compare two different guidance strategies: CL…

Cited by 3944 Source ↗PDF ↗code ↗Scholar ↗

2020

Emergent Tool Use From Multi-Agent Autocurricula

Bowen Baker, Ingmar Kanitscheider, Todor Markov, Yi Wu, Glenn Powell, Bob McGrew +1

ICLR 2020spotlight

Through multi-agent competition, the simple objective of hide-and-seek, and standard reinforcement learning algorithms at scale, we find that agents create a self-supervised autocurriculum inducing multiple distinct rounds of emergent strategy, many of which require sophisticated tool use and coordi…

Cited by 961 Source ↗code ↗Scholar ↗

2018

Domain Randomization and Generative Models for Robotic Grasping

Josh Tobin, Lukas Biewald, Rocky Duan, Marcin Andrychowicz, Ankur Handa, Vikash Kumar +6

IROS 2018poster

Deep learning-based robotic grasping has made significant progress thanks to algorithmic improvements and increased data availability. However, state-of-the-art models are often trained on as few as hundreds or thousands of unique object instances, and as a result generalization can be a challenge.…

Cited by 194 Source ↗Scholar ↗

2018

Overcoming Exploration in Reinforcement Learning with Demonstrations

Ashvin Nair, Bob McGrew, Marcin Andrychowicz, Wojciech Zaremba, Pieter Abbeel

ICRA 2018poster

Exploration in environments with sparse rewards has been a persistent problem in reinforcement learning (RL). Many tasks are natural to specify with a sparse reward, and manually shaping a reward function can result in suboptimal performance. However, finding a non-zero reward is exponentially more…

Cited by 1038 Source ↗Scholar ↗

2017

Hindsight Experience Replay

Marcin Andrychowicz, Filip Wolski, Alex Ray, Jonas Schneider, Rachel Fong, Peter Welinder +4

NeurIPS 2017poster

Dealing with sparse rewards is one of the biggest challenges in Reinforcement Learning (RL). We present a novel technique called Hindsight Experience Replay which allows sample-efficient learning from rewards which are sparse and binary and therefore avoid the need for complicated reward engineering…

Cited by 3290 Source ↗PDF ↗Scholar ↗