Philip Bachman

Computer Science · Physical Sciences

18h-index4.8kcitations46works0.02yr avg
OpenAlex↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Domain Adaptation and Few-Shot Learning(13), Reinforcement Learning in Robotics(12), Machine Learning and Algorithms(10), Topic Modeling(9), Multimodal Machine Learning Applications(9)

Publications46 total

Video Occupancy Models
arXiv (Cornell University)·2024Open Access
Sampling Informative Positives Pairs in Contrastive Learning
2023
Ignorance is Bliss: Robust Control via Information Gating
arXiv (Cornell University)·2023Open Access
Pretraining Representations for Data-Efficient Reinforcement Learning
arXiv (Cornell University)·2021· 1 citedOpen Access
Decomposed Mutual Information Estimation for Contrastive Representation Learning
arXiv (Cornell University)·2021· 11 citedOpen Access
Pretraining Representations for Data-Efficient Reinforcement Learning
arXiv (Cornell University)·2021· 33 citedOpen Access
Decomposing Mutual Information for Representation Learning
2021
Pretraining Reward-Free Representations for Data-Efficient Reinforcement Learning
International Conference on Learning Representations·2021
Representation Learning with Video Deep InfoMax
arXiv (Cornell University)·2020· 11 citedOpen Access
Data-Efficient Reinforcement Learning with Self-Predictive\n Representations
arXiv (Cornell University)·2020· 49 citedOpen Access
Deep Reinforcement and InfoMax Learning
arXiv (Cornell University)·2020· 10 citedOpen Access
Deep Reinforcement and InfoMax Learning
arXiv (Cornell University)·2020· 16 citedOpen Access
Learning Representations by Maximizing Mutual Information Across Views
Neural Information Processing Systems·2019· 423 cited
Learning Representations by Maximizing Mutual Information Across Views
arXiv (Cornell University)·2019· 678 citedOpen Access
Learning Invariances for Policy Generalization
arXiv (Cornell University)·2018· 3 citedOpen Access
VFunc: a Deep Generative Model for Functions
arXiv (Cornell University)·2018· 7 citedOpen Access
Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data
International Conference on Machine Learning·2018· 85 cited
Deep Reinforcement Learning That Matters
Proceedings of the AAAI Conference on Artificial Intelligence·2018· 1.4k citedOpen Access
Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data
arXiv (Cornell University)·2018· 315 citedOpen Access
Learning Invariances for Policy Generalization
International Conference on Learning Representations·2018· 3 cited
page 1 of 3Next →

Frequent Co-authors

Alessandro Sordoni(12), Doina Precup(10), Adam Trischler(8), R Devon Hjelm(7), Aaron Courville(7), Rémi Tachet des Combes(5), Riashat Islam(4), Joëlle Pineau(4), Xingdi Yuan(4), Kaheer Suleman(4), Max Schwarzer(4), Ankesh Anand(4), Hannes Schulz(4), Amjad Almahairi(3), Jing He(3), Nitarshan Rajkumar(3), Michael Noukhovitch(3), Laurent Charlin(3), Peter Henderson(2), David Meger(2)