papers

Publications (15)

cs.CV2018

Interpretable Intuitive Physics Model

Tian Ye, Xiaolong Wang, James Davidson +1

Humans have a remarkable ability to use physical commonsense and predict the effect of collisions. But do they understand the underlying factors? Can they predict if the underlying…

cs.AI2017

A Brief Study of In-Domain Transfer and Learning from Fewer Samples using A Few Simple Priors

Marc Pickett, Ayush Sekhari, James Davidson

Domain knowledge can often be encoded in the structure of a network, such as convolutional layers for vision, which has been shown to increase generalization and decrease sample co…

cs.CV2019

Visual Representations for Semantic Target Driven Navigation

Arsalan Mousavian, Alexander Toshev, Marek Fiser +3

What is a good visual representation for autonomous agents? We address this question in the context of semantic visual navigation, which is the problem of a robot finding its way t…

cs.LG2018

TensorFlow Agents: Efficient Batched Reinforcement Learning in TensorFlow

Danijar Hafner, James Davidson, Vincent Vanhoucke

We introduce TensorFlow Agents, an efficient infrastructure paradigm for building parallel reinforcement learning algorithms in TensorFlow. We simulate multiple environments in par…

stat.ML2019

Noise Contrastive Priors for Functional Uncertainty

Danijar Hafner, Dustin Tran, Timothy Lillicrap +2

Obtaining reliable uncertainty estimates of neural network predictions is a long standing challenge. Bayesian neural networks have been proposed as a solution, but it remains open…

cs.CV2019

Cognitive Mapping and Planning for Visual Navigation

Saurabh Gupta, Varun Tolani, James Davidson +3

We introduce a neural architecture for navigation in novel environments. Our proposed architecture learns to map from first-person views and plans a sequence of actions towards goa…

cs.RO2016

Supervision via Competition: Robot Adversaries for Learning Tasks

Lerrel Pinto, James Davidson, Abhinav Gupta

There has been a recent paradigm shift in robotics to data-driven learning for planning and control. Due to large number of experiences required for training, most of these approac…

cs.AI2018

PRM-RL: Long-range Robotic Navigation Tasks by Combining Reinforcement Learning and Sampling-based Planning

Aleksandra Faust, Oscar Ramirez, Marek Fiser +4

We present PRM-RL, a hierarchical method for long-range navigation task completion that combines sampling based path planning with reinforcement learning (RL). The RL agents learn…

cs.LG2017

Robust Adversarial Reinforcement Learning

Lerrel Pinto, James Davidson, Rahul Sukthankar +1

Deep neural networks coupled with fast simulation and improved computation have led to recent successes in the field of reinforcement learning (RL). However, most current RL-based…

cs.LG2019

Learning Latent Dynamics for Planning from Pixels

Danijar Hafner, Timothy Lillicrap, Ian Fischer +4

Planning has been very successful for control tasks with known environment dynamics. To leverage planning in unknown environments, the agent needs to learn the dynamics from intera…

cs.LG2019

Discrete Sequential Prediction of Continuous Actions for Deep RL

Luke Metz, Julian Ibarz, Navdeep Jaitly +1

It has long been assumed that high dimensional continuous control problems cannot be solved effectively by discretizing individual dimensions of the action space due to the exponen…

cs.LG2018

Modulated Policy Hierarchies

Alexander Pashevich, Danijar Hafner, James Davidson +2

Solving tasks with sparse rewards is a main challenge in reinforcement learning. While hierarchical controllers are an intuitive approach to this problem, current methods often req…

cs.LG2017

Learning Hierarchical Information Flow with Recurrent Neural Modules

Danijar Hafner, Alex Irpan, James Davidson +1

We propose ThalNet, a deep learning model inspired by neocortical communication via the thalamus. Our model consists of recurrent neural modules that send features through a routin…

physics.comp-ph2021

Tungsten boride shields in a spherical tokamak

Colin G Windsor, Jack O Astbury, James Davidson +4

The favourable properties of tungsten borides for shielding the central High Temperature Superconductor (HTS) core of a spherical tokamak fusion power plant are modelled using the…

cs.RO2018

Learning 6-DOF Grasping Interaction via Deep Geometry-aware 3D Representations

Xinchen Yan, Jasmine Hsu, Mohi Khansari +5

This paper focuses on the problem of learning 6-DOF grasping with a parallel jaw gripper in simulation. We propose the notion of a geometry-aware representation in grasping based o…