Search Results for author:
Found 20 papers, 10 papers with code
Kubric: A scalable dataset generator
Data is the driving force of machine learning, with the amount and quality of training data often being more important for the performance of a system than architecture and training details.
Sequoia: A Software Framework to Unify Continual Learning Research
We propose a taxonomy of settings, where each setting is described as a set of assumptions.
Active Domain Randomization
Our experiments show that domain randomization may lead to suboptimal, high-variance policies, which we attribute to the uniform sampling of environment parameters.
Latent Variable Sequential Set Transformers For Joint Multi-Agent Motion Prediction
AutoBots can produce either the trajectory of one ego-agent or a distribution over the future trajectories for all agents in the scene.
Pix2Shape: Towards Unsupervised Learning of 3D Scenes from Images using a View-based Representation
We propose Pix2Shape, an approach to solve this problem with four components: (i) an encoder that infers the latent 3D representation from an image, (ii) a decoder that generates an explicit 2. 5D surfel-based reconstruction of a scene from the latent code (iii) a differentiable renderer that synthesizes a 2D image from the surfel representation, and (iv) a critic network trained to discriminate between images generated by the decoder-renderer and those from a training distribution.
Navigation Agents for the Visually Impaired: A Sidewalk Simulator and Experiments
In our endeavor to create a navigation assistant for the BVI, we found that existing Reinforcement Learning (RL) environments were unsuitable for the task.
The Sandbox Environment for Generalizable Agent Research (SEGAR)
A broad challenge of research on generalization for sequential decision-making tasks in interactive environments is designing benchmarks that clearly landmark progress.
Generating Automatic Curricula via Self-Supervised Active Domain Randomization
Goal-directed Reinforcement Learning (RL) traditionally considers an agent interacting with an environment, prescribing a real-valued reward to an agent proportional to the completion of some goal.
Touch-based Curiosity for Sparse-Reward Tasks
Robots in many real-world settings have access to force/torque sensors in their gripper and tactile sensing is often necessary in tasks that involve contact-rich motion.
Visual Question Answering From Another Perspective: CLEVR Mental Rotation Tests
Different types of mental rotation tests have been used extensively in psychology to understand human visual reasoning and perception.
HoME: a Household Multimodal Environment
We introduce HoME: a Household Multimodal Environment for artificial agents to learn from vision, audio, semantics, physics, and interaction with objects and other agents, all within a realistic context.
Pix2Scene: Learning Implicit 3D Representations from Images
Modelling 3D scenes from 2D images is a long-standing problem in computer vision with implications in, e. g., simulation and robotics.
Towards Learning to Imitate from a Single Video Demonstration
We approach this challenge using contrastive training to learn a reward function comparing an agent's behaviour with a single demonstration.
Robo-PlaNet: Learning to Poke in a Day
Recently, the Deep Planning Network (PlaNet) approach was introduced as a model-based reinforcement learning method that learns environment dynamics directly from pixel observations.
Visual Imitation with Reinforcement Learning using Recurrent Siamese Networks
It would be desirable for a reinforcement learning (RL) based agent to learn behaviour by merely watching a demonstration.
Unsupervised Learning of Dense Visual Representations
VADeR provides a natural representation for dense prediction tasks and transfers well to downstream tasks.
Perspectives on Sim2Real Transfer for Robotics: A Summary of the R:SS 2020 Workshop
This report presents the debates, posters, and discussions of the Sim2Real workshop held in conjunction with the 2020 edition of the "Robotics: Science and System" conference.
gradSim: Differentiable simulation for system identification and visuomotor control
We consider the problem of estimating an object's physical properties such as mass, friction, and elasticity directly from video sequences.
GrowSpace: Learning How to Shape Plants
We argue that plant responses to an environmental stimulus are a good example of a real-world problem that can be approached within a reinforcement learning (RL)framework.
CtRL-Sim: Reactive and Controllable Driving Agents with Offline Reinforcement Learning
With this dataset, we train a return-conditioned multi-agent behaviour model that allows for fine-grained manipulation of agent behaviours by modifying the desired returns for the various reward components.
