It's me!

My name is Ben Eisner, and I’m a Machine Learning and Robotics researcher. I build robotic systems that learn to interact with the unstructured world.

I’m currently a 1st-Year Ph.D. student in the Robotics Institute at Carnegie Mellon University. I’m a member of the Robots Perceiving and Doing Lab, led by Prof. David Held. Right now, I’m working on some techniques for policy transfer. My research is supported in part by the NSF Graduate Research Fellowship.

Here is a recent version of my academic cv, my Google Scholar profile, and my Github profile.

You can reach me at

❗❗❗ Recent News ❗❗❗

  • 10/31/20: We submitted a paper on learning to grasp objects from grasp proposal and image reconstruction to ICRA 2021!

  • 8/31/20: I started my Ph.D. program in Robotics at Carnegie Mellon University!

  • 4/20/20: Our paper using TD-error as an exploration signal was accepted for publication at IJCAI 2020!

  • 3/30/20: I was selected to receive the NSF Graduate Research Fellowship for the fellowship class of 2020!



Robotic Grasping through Combined image-Based Grasp Proposal and 3D Reconstruction
Tarik Tosun, Daniel Yang, Ben Eisner, Volkan Isler, Daniel Lee
Under Review for ICRA 2021

Reward Prediction Error as an Exploration Objective in Deep RL
Riley Simmons-Edler, Ben Eisner, Daniel Yang, Anthony Bisulco, Eric Mitchell, Sebastian Seung, Daniel Lee
IJCAI 2020 (Earlier draft presented at NeurIPS 2020 Workshop on Deep RL)


Pixels to Plans: Learning Non-Prehensile Manipulation by Imitating a Planner
Tarik Tosun*, Eric Mitchell*, Ben Eisner, Jinwook Huh, Bhoram Lee, Daewon Lee, Volkan Isler, Sebastian Seung, Daniel Lee
IROS 2019
arxiv | website | video

Q-Learning for Continuous Actions with Cross-Entropy Guided Policies
Riley Simmons-Edler*, Ben Eisner*, Eric Mitchell, Sebastian Seung, Daniel Lee
ICML 2019 Workshop on RL4RealLife


Deep Learning Methods for 3D Segmentation of Neural Tissue in EM Images
Ben Eisner
Princeton University Senior Thesis
thesis | project


emoji2vec: Learning emoji representations from their description
Ben Eisner, Tim Rocktäschel, Isabelle Augenstein, Matko Bošnjak, Sebastian Riedel
Best Paper at EMNLP 2016 Workshop on SocialNLP
arxiv | project