John D. Co-Reyes

I am a PhD student at Berkeley AI Research Lab (BAIR) working with Sergey Levine, where I work on machine learning, deep reinforcement learning, and robotics.

I did my undergrad at Caltech where I worked with Yisong Yue and Pietro Perona on computer vision.

Email  /  Google Scholar  /  LinkedIn  /  Github  /  CV


My long-term goal is help build general AI and use that to accelerate research in other fields. I'm interested in combining deep learning with reinforcement learning in order to solve complex decision making problems. Areas of interest include computer vision, representation learning, and natural language processing all at the intersection with control and reinforcement learning in order to build complex autonomous agents that can understand the world, learn from previous behavior, and operate intelligently with humans. I'm currently interested in studying the emergence of intelligent behavior in complex environments with simple unsupervised learning objectives.

Evolving Reinforcement Learning Algorithms
John D. Co-Reyes, Yingjie Miao, Daiyi Peng, Esteban Real, Sergey Levine, Quoc V. Le, Honglak Lee, Aleksandra Faust
International Conference on Learning Representations, 2021
Oral Presentation, 1.8% acceptance rate.
Mentioned in Google AI Year in Review , Analytics India Magazine

Ecological Reinforcement Learning
John D. Co-Reyes*, Suvansh Sanjeev*, Glen Berseth, Abhishek Gupta, Sergey Levine
NeurIPS Deep RL Workshop, 2019
project page / code

Entity Abstraction in Visual Model-Based Reinforcement Learning
Rishi Veerapaneni*, John D. Co-Reyes*, Michael Chang*, Michael Janner, Chelsea Finn, Jiajun Wu, Joshua B. Tenenbaum, Sergey Levine
Conference on Robot Learning, 2019
project page / code / poster

Guiding Policies with Language via Meta-Learning
John D. Co-Reyes, Abhishek Gupta, Suvansh Sanjeev, Nick Altieri, Jacob Andreas, Pieter Abbeel Sergey Levine
International Conference on Learning Representations, 2019
Best Paper at Meta-Learning Workshop at NeurIPS, 2018
project page / poster / workshop slides

Self-Consistent Trajectory Autoencoder: Hierararchical Reinforcement Learning with Trajectory Embeddings
John D. Co-Reyes*, YuXuan Liu*, Abhishek Gupta*, Benjamin Eysenbach, Pieter Abbeel Sergey Levine
International Conference on Machine Learning, 2018
project page / code / poster / video

EX2: Exploration with Exemplar Models for Deep Reinforcement Learning
Justin Fu*, John D. Co-Reyes*, Sergey Levine
Advances in Neural Information Processing Systems (NIPS), 2017
Spotlight Presentation. 4.69% acceptance rate (152/3240)
project page / code / poster / conference slides

cs188 Graduate Student Instructor, CS182, Designing, Visualizing and Understanding Deep Neural Networks, Spring 2021

cs188 Graduate Student Instructor, CS188 Introduction to Artificial Intelligence, Spring 2018

Figures, "Artificial Intelligence: A Modern Approach", 3rd Edition

I like this website.