• Publications
  • Influence
Addressing Function Approximation Error in Actor-Critic Methods
TLDR
This paper builds on Double Q-learning, by taking the minimum value between a pair of critics to limit overestimation, and draws the connection between target networks and overestimation bias. Expand
Off-Policy Deep Reinforcement Learning without Exploration
TLDR
This paper introduces a novel class of off-policy algorithms, batch-constrained reinforcement learning, which restricts the action space in order to force the agent towards behaving close to on-policy with respect to a subset of the given data. Expand
Deep Reinforcement Learning that Matters
TLDR
Challenges posed by reproducibility, proper experimental techniques, and reporting procedures are investigated and guidelines to make future results in deep RL more reproducible are suggested. Expand
Curious George: An attentive semantic robot
TLDR
An intelligent system that attempts to perform robust object recognition in a realistic scenario, where a mobile robot moving through an environment must use the images collected from its camera directly to recognise objects. Expand
Improved Adversarial Systems for 3D Object Generation and Reconstruction
TLDR
This paper describes a new approach for training generative adversarial networks (GAN) to understand the detailed 3D shape of objects by employing the Wasserstein distance normalized with gradient penalization as a training objective. Expand
Informed visual search: Combining attention and object recognition
TLDR
Experimental results demonstrate that the system described in this paper is a highly competent object recognition system that is capable of locating numerous challenging objects amongst distractors. Expand
Fine-Grained Categorization for 3D Scene Understanding
TLDR
This paper proposes two novel methods for fine-grained classification, both based on part information, as well as a new fine-Grained category data set of car types, and demonstrates superior performance of these methods to state-of-the-art classifiers. Expand
Multi-View Silhouette and Depth Decomposition for High Resolution 3D Object Representation
TLDR
This work introduces a novel method for the fast up-sampling of 3D objects in voxel space through networks that perform super-resolution on the six orthographic depth projections, and achieves state-of-the-art performance on 3D object reconstruction from RGB images on the ShapeNet dataset. Expand
Explicit Occlusion Reasoning for 3D Object Detection
TLDR
This work simplifies the problem of recognizing an object that is partially occluded in an image by considering only a small subset of the most likely occlusions (top, bottom, left, and right halves) and noting that some mismatch is tolerable. Expand
GEOMetrics: Exploiting Geometric Structure for Graph-Encoded Objects
TLDR
This paper argues that the graph representation of geometric objects allows for additional structure, which should be leveraged for enhanced reconstruction, and proposes a system which properly benefits from the advantages of the geometric structure of graph encoded objects by introducing a graph convolutional update preserving vertex information. Expand
...
1
2
3
4
5
...