research
∙
12/24/2022
GraphCast: Learning skillful medium-range global weather forecasting
We introduce a machine-learning (ML)-based weather simulator–called "Gra...
share
research
∙
10/02/2022
MultiScale MeshGraphNets
In recent years, there has been a growing interest in using machine lear...
research
∙
11/16/2021
Normalizing flows for atomic solids
We present a machine-learning approach, based on normalizing flows, for ...
research
∙
02/14/2020
Never Give Up: Learning Directed Exploration Strategies
We propose a reinforcement learning agent to solve hard exploration game...
research
∙
02/12/2020
Targeted free energy estimation via learned mappings
Free energy perturbation (FEP) was proposed by Zwanzig more than six dec...
research
∙
10/18/2018
Fast deep reinforcement learning using online adjustments from the past
We propose Ephemeral Value Adjusments (EVA): a means of allowing deep re...
research
∙
06/06/2018
Meta Learning by the Baldwin Effect
The scope of the Baldwin effect was recently called into question by two...
research
∙
04/25/2018
Generative Temporal Models with Spatial Memory for Partially Observed Environments
In model-based reinforcement learning, generative and temporal models of...
research
∙
02/28/2018
Memory-based Parameter Adaptation
Deep neural networks have excelled on a wide range of problems, from vis...
research
∙
07/26/2017
DARLA: Improving Zero-Shot Transfer in Reinforcement Learning
Domain adaptation is an important open problem in deep reinforcement lea...
research
∙
03/06/2017
Neural Episodic Control
Deep reinforcement learning methods attain super-human performance in a ...
research
∙
01/30/2017
PathNet: Evolution Channels Gradient Descent in Super Neural Networks
For artificial general intelligence (AGI) it would be efficient if multi...
research
∙
06/14/2016
Model-Free Episodic Control
State of the art deep reinforcement learning algorithms take many millio...
research
∙
02/15/2016
Deep Exploration via Bootstrapped DQN
Efficient exploration in complex environments remains a major challenge ...
research
∙
09/09/2015