Search Results for author:
Found 14 papers, 8 papers with code
Parametric and Multivariate Uncertainty Calibration for Regression and Object Detection
Our experiments show that common detection models overestimate the spatial uncertainty in comparison to the observed error.
Confidence Calibration for Object Detection and Segmentation
Calibrated confidence estimates obtained from neural networks are crucial, particularly for safety-critical applications such as autonomous driving or medical image diagnosis.
Bayesian Confidence Calibration for Epistemic Uncertainty Modelling
We introduce Bayesian confidence calibration - a framework to obtain calibrated confidence estimates in conjunction with an uncertainty of the calibration method.
On Feature Relevance Uncertainty: A Monte Carlo Dropout Sampling Approach
Understanding decisions made by neural networks is key for the deployment of intelligent systems in real world applications.
Dota 2 with Large Scale Deep Reinforcement Learning
On April 13th, 2019, OpenAI Five became the first AI system to defeat the world champions at an esports game.
Solving Rubik's Cube with a Robot Hand
We demonstrate that models trained only in simulation can be used to solve a manipulation problem of unprecedented complexity on a real robot.
Learning Dexterous In-Hand Manipulation
We use reinforcement learning (RL) to learn dexterous in-hand manipulation policies which can perform vision-based object reorientation on a physical Shadow Dexterous Hand.
Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research
The purpose of this technical report is two-fold.
Domain Randomization and Generative Models for Robotic Grasping
In this work, we explore a novel data generation pipeline for training a deep neural network to perform grasp planning that applies the idea of domain randomization to object synthesis.
Hindsight Experience Replay
Dealing with sparse rewards is one of the biggest challenges in Reinforcement Learning (RL).
One-Shot Imitation Learning
A neural net is trained that takes as input one demonstration and the current state (which initially is the initial state of the other demonstration of the pair), and outputs an action with the goal that the resulting sequence of states and actions matches as closely as possible with the second demonstration.
Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World
Bridging the 'reality gap' that separates simulated robotics from experiments on hardware could accelerate robotic research through improved data availability.
Transfer from Simulation to Real World through Learning Deep Inverse Dynamics Model
Nevertheless, often the overall gist of what the policy does in simulation remains valid in the real world.
