Timezone: »
Poster
PHYRE: A New Benchmark for Physical Reasoning
Anton Bakhtin · Laurens van der Maaten · Justin Johnson · Laura Gustafson · Ross Girshick
Wed Dec 11 05:00 PM -- 07:00 PM (PST) @ East Exhibition Hall B + C #125
Understanding and reasoning about physics is an important ability of intelligent agents. We develop the PHYRE benchmark for physical reasoning that contains a set of simple classical mechanics puzzles in a 2D physical environment. The benchmark is designed to encourage the development of learning algorithms that are sample-efficient and generalize well across puzzles. We test several modern learning algorithms on PHYRE and find that these algorithms fall short in solving the puzzles efficiently. We expect that PHYRE will encourage the development of novel sample-efficient agents that learn efficient but useful models of physics. For code and to play PHYRE for yourself, please visit https://player.phyre.ai.
Author Information
Anton Bakhtin (Facebook AI Research)
Laurens van der Maaten (Facebook)
Justin Johnson (University of Michigan / FAIR)
Laura Gustafson (Facebook AI Research)
Ross Girshick (FAIR)
More from the Same Authors
-
2021 : RedCaps: Web-curated image-text data created by the people, for the people »
Karan Desai · Gaurav Kaul · Zubin Aysola · Justin Johnson -
2022 : Bias Amplification in Image Classification »
Melissa Hall · Laurens van der Maaten · Laura Gustafson · Maxwell Jones · Aaron Adcock -
2022 : Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and Planning »
Anton Bakhtin · David Wu · Adam Lerer · Jonathan Gray · Athul Jacob · Gabriele Farina · Alexander Miller · Noam Brown -
2022 Poster: Self-Explaining Deviations for Coordination »
Hengyuan Hu · Samuel Sokota · David Wu · Anton Bakhtin · Andrei Lupu · Brandon Cui · Jakob Foerster -
2021 Poster: Fixes That Fail: Self-Defeating Improvements in Machine-Learning Systems »
Ruihan Wu · Chuan Guo · Awni Hannun · Laurens van der Maaten -
2021 Poster: No-Press Diplomacy from Scratch »
Anton Bakhtin · David Wu · Adam Lerer · Noam Brown -
2021 Poster: CrypTen: Secure Multi-Party Computation Meets Machine Learning »
Brian Knott · Shobha Venkataraman · Awni Hannun · Shubho Sengupta · Mark Ibrahim · Laurens van der Maaten -
2020 Workshop: Self-Supervised Learning -- Theory and Practice »
Pengtao Xie · Shanghang Zhang · Pulkit Agrawal · Ishan Misra · Cynthia Rudin · Abdelrahman Mohamed · Wenzhen Yuan · Barret Zoph · Laurens van der Maaten · Xingyi Yang · Eric Xing -
2020 Poster: Combining Deep Reinforcement Learning and Search for Imperfect-Information Games »
Noam Brown · Anton Bakhtin · Adam Lerer · Qucheng Gong -
2020 : Building AI with Security and Privacy in mind »
Geeta Chauhan · Laurens van der Maaten · Davide Testuggine · Andrew Trask -
2020 Expo Workshop: Building AI with Security and Privacy in mind »
Geeta Chauhan · Laurens van der Maaten · Davide Testuggine · Andrew Trask · Joe Spisak