Search Results - "Zhou, Gaoyue"

DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning by Zhou, Gaoyue, Pan, Hengkai, LeCun, Yann, Pinto, Lerrel

“…The ability to predict future outcomes given control actions is fundamental for physical reasoning. However, such predictive models, often called world models,…”
Get full text

Putting the Con in Context: Identifying Deceptive Actors in the Game of Mafia by Ibraheem, Samee, Zhou, Gaoyue, DeNero, John

“…While neural networks demonstrate a remarkable ability to model linguistic content, capturing contextual information related to a speaker's conversational role…”
Get full text

RoboHive: A Unified Framework for Robot Learning by Kumar, Vikash, Shah, Rutav, Zhou, Gaoyue, Moens, Vincent, Caggiano, Vittorio, Vakil, Jay, Gupta, Abhishek, Rajeswaran, Aravind

“…We present RoboHive, a comprehensive software platform and ecosystem for research in the field of Robot Learning and Embodied Artificial Intelligence. Our…”
Get full text

Real World Offline Reinforcement Learning with Realistic Data Source by Zhou, Gaoyue, Ke, Liyiming, Srinivasa, Siddhartha, Gupta, Abhinav, Rajeswaran, Aravind, Kumar, Vikash

“…Offline reinforcement learning (ORL) holds great promise for robot learning due to its ability to learn from arbitrary pre-generated experience. However,…”
Get full text

Real World Offline Reinforcement Learning with Realistic Data Source by Zhou, Gaoyue, Ke, Liyiming, Srinivasa, Siddhartha, Gupta, Abhinav, Rajeswaran, Aravind, Kumar, Vikash

“…Offline reinforcement learning (ORL) holds great promise for robot learning due to its ability to learn from arbitrary pre-generated experience. However,…”
Get full text

Train Offline, Test Online: A Real Robot Learning Benchmark by Zhou, Gaoyue, Dean, Victoria, Srirama, Mohan Kumar, Rajeswaran, Aravind, Pari, Jyothish, Hatch, Kyle, Jain, Aryan, Yu, Tianhe, Abbeel, Pieter, Pinto, Lerrel, Finn, Chelsea, Gupta, Abhinav

“…Three challenges limit the progress of robot learning research: robots are expensive (few labs can participate), everyone uses different robots (findings do…”
Get full text

Train Offline, Test Online: A Real Robot Learning Benchmark by Zhou, Gaoyue, Dean, Victoria, Srirama, Mohan Kumar, Rajeswaran, Aravind, Pari, Jyothish, Hatch, Kyle, Jain, Aryan, Yu, Tianhe, Abbeel, Pieter, Pinto, Lerrel, Finn, Chelsea, Gupta, Abhinav

“…Three challenges limit the progress of robot learning research: robots are expensive (few labs can participate), everyone uses different robots (findings do…”
Get full text

Parrot: Data-Driven Behavioral Priors for Reinforcement Learning by Singh, Avi, Liu, Huihan, Zhou, Gaoyue, Yu, Albert, Rhinehart, Nicholas, Levine, Sergey

“…Reinforcement learning provides a general framework for flexible decision making and control, but requires extensive data collection for each new task that an…”
Get full text