Search Results for author:
Found 8 papers, 3 papers with code
A new perspective on building efficient and expressive 3D equivariant graph neural networks
Geometric deep learning enables the encoding of physical symmetries in modeling 3D objects.
Graph Value Iteration
We propose a domain-independent method that augments graph search with graph value iteration to solve hard planning instances that are out of reach for domain-specialized solvers.
Left Heavy Tails and the Effectiveness of the Policy and Value Networks in DNN-based best-first search for Sokoban Planning
To better understand why these approaches work, we studied the interplay of the policy and value networks of DNN-based best-first search on Sokoban and show the surprising effectiveness of the policy network, further enhanced by the value network, as a guiding heuristic for the search.
A Novel Automated Curriculum Strategy to Solve Hard Sokoban Planning Instances
In particular, as the size of the instance pool increases, the ``hardness gap'' decreases, which facilitates a smoother automated curriculum based learning process.
The Remarkable Effectiveness of Combining Policy and Value Networks in A*-based Deep RL for AI Planning
To better understanding why these approaches work we study the interplay of the policy and value networks in A\textsc{*}-based deep RL and show the surprising effectiveness of the policy network, further enhanced by the value network, as a guiding heuristic for A\textsc{*}.
Solving Hard AI Planning Instances Using Curriculum-Driven Deep Reinforcement Learning
Despite significant progress in general AI planning, certain domains remain out of reach of current AI planning systems.
GeneGAN: Learning Object Transfiguration and Attribute Subspace from Unpaired Data
In this work, we propose a model that can learn object transfiguration from two unpaired sets of images: one set containing images that "have" that kind of object, and the other set being the opposite, with the mild constraint that the objects be located approximately at the same place.
Training Bit Fully Convolutional Network for Fast Semantic Segmentation
Fully convolutional neural networks give accurate, per-pixel prediction for input images and have applications like semantic segmentation.
