In this paper, we propose a novel model-based multi-agent reinforcement
...
This work introduces a novel approach for epistemic uncertainty estimati...
In the field of reinforcement learning (RL), representation learning is ...
Reinforcement learning on high-dimensional and complex problems relies o...
Our work examines the way in which large language models can be used for...
In this work, we demonstrate how to reliably estimate epistemic uncertai...
In this paper, hypernetworks are trained to generate behaviors across a ...
Driving SMARTS is a regular competition designed to tackle problems caus...
Multi-view implicit scene reconstruction methods have become increasingl...
Guided exploration with expert demonstrations improves data efficiency f...
Abstraction has been widely studied as a way to improve the efficiency a...
Continuous-time reinforcement learning offers an appealing formalism for...
We present an algorithm for Inverse Reinforcement Learning (IRL) from ex...
In this work, we study the use of the Bellman equation as a surrogate
ob...
We present a reward-predictive, model-based deep learning method featuri...
This paper presents the portable autonomous probing system (APS), a low-...
Humans build 3D understandings of the world through active object
explor...
Marginalized importance sampling (MIS), which measures the density ratio...
Predicting the future interaction of objects when they come into contact...
The goal of this work is to address the recent success of domain
randomi...
Dynamics modeling in outdoor and unstructured environments is difficult
...
We introduce a new class of vision-based sensor and associated algorithm...
Utilization of latent space to capture a lower-dimensional representatio...
Prioritized Experience Replay (PER) is a deep reinforcement learning
tec...
When a toddler is presented a new toy, their instinctual behaviour is to...
We present Nav2Goal, a data-efficient and end-to-end learning method for...
We present a method for learning to drive on smooth terrain while
simult...
Despite an impressive performance from the latest GAN for generating
hyp...
Neural Network based controllers hold enormous potential to learn comple...
Reanalysis datasets combining numerical physics models and limited
obser...
Motivated by the recursive Newton-Euler formulation, we propose a novel
...
Domain randomization (DR) is a successful technique for learning robust
...
Inspired by ideas in cognitive science, we propose a novel and general
a...
Diversity of environments is a key challenge that causes learned robotic...
Mesh models are a promising approach for encoding the structure of 3D
ob...
Reinforcement learning traditionally considers the task of balancing
exp...
We present an algorithm for rapidly learning controllers for robotics
sy...
We consider the problem of scaling deep generative shape models to
high-...
The multi-agent swarm system is a robust paradigm which can drive effici...
In recent years, significant progress has been made in solving challengi...
As demand drives systems to generalize to various domains and problems, ...
This paper describes a new approach for training generative adversarial
...
The Semantic Robot Vision Competition provided an excellent opportunity ...