2.3k citations · 2.9k across the 20 of their papers we have counts for
6 papers · 1 filter
Higher Order Function Networks for View Planning and Multi-View Reconstruction
Selim Engin, Eric Mitchell, Daewon Lee +2
We consider the problem of planning views for a robot to acquire images of an object for visual inspection and reconstruction. In contrast to offline methods which require a 3D mod…
Higher-Order Function Networks for Learning Composable 3D Object Representations
Eric Mitchell, Selim Engin, Volkan Isler +1
We present a new approach to 3D object representation where a neural network encodes the geometry of an object directly into the weights and biases of a second 'mapping' network. T…
Reward Prediction Error as an Exploration Objective in Deep RL
Riley Simmons-Edler, Ben Eisner, Daniel Yang +4
A major challenge in reinforcement learning is exploration, when local dithering methods such as epsilon-greedy sampling are insufficient to solve a given task. Many recent methods…
Pixels to Plans: Learning Non-Prehensile Manipulation by Imitating a Planner
Tarik Tosun, Eric Mitchell, Ben Eisner +6
We present a novel method enabling robots to quickly learn to manipulate objects by leveraging a motion planner to generate "expert" training trajectories from a small amount of hu…
Siamese Encoding and Alignment by Multiscale Learning with Self-Supervision
Eric Mitchell, Stefan Keselj, Sergiy Popovych +2
We propose a method of aligning a source image to a target image, where the transform is specified by a dense vector field. The two images are encoded as feature hierarchies by sia…
Q-Learning for Continuous Actions with Cross-Entropy Guided Policies
Riley Simmons-Edler, Ben Eisner, Eric Mitchell +2
Off-Policy reinforcement learning (RL) is an important class of methods for many problem domains, such as robotics, where the cost of collecting data is high and on-policy methods…