NeurIPS 2016

Deep Exploration via Bootstrapped DQN

NeurIPS 2016 tensorflow/models

Efficient exploration in complex environments remains a major challenge for reinforcement learning.

ATARI GAMES EFFICIENT EXPLORATION

Visual Dynamics: Probabilistic Future Frame Synthesis via Cross Convolutional Networks

NeurIPS 2016 tensorflow/models

We study the problem of synthesizing a number of likely future frames from a single input image.

Unsupervised Learning for Physical Interaction through Video Prediction

NeurIPS 2016 tensorflow/models

A core challenge for an agent learning to interact with the world is to predict how its actions affect objects in its environment.

VIDEO PREDICTION

Learning to learn by gradient descent by gradient descent

NeurIPS 2016 deepmind/learning-to-learn

The move from hand-designed features to learned features in machine learning has been wildly successful.

META-LEARNING

Memory-Efficient Backpropagation Through Time

NeurIPS 2016 openai/gradient-checkpointing

We propose a novel approach to reduce memory consumption of the backpropagation through time (BPTT) algorithm when training recurrent neural networks (RNNs).

Higher-Order Factorization Machines

NeurIPS 2016 geffy/tffm

Factorization machines (FMs) are a supervised learning approach that can use second-order feature combinations even when the data is very high-dimensional.

LINK PREDICTION

Generating Images with Perceptual Similarity Metrics based on Deep Networks

NeurIPS 2016 Evolving-AI-Lab/synthesizing

This metric better reflects perceptually similarity of images and thus leads to better results.

IMAGE GENERATION

Improved Variational Inference with Inverse Autoregressive Flow

NeurIPS 2016 openai/iaf

The framework of normalizing flows provides a general strategy for flexible variational inference of posteriors over latent variables.

#4 best model for Image Generation on CIFAR-10 (Model Entropy metric)

IMAGE GENERATION

Learning to Communicate with Deep Multi-Agent Reinforcement Learning

NeurIPS 2016 iassael/learning-to-communicate

We consider the problem of multiple agents sensing and acting in environments with the goal of maximising their shared utility.

MULTI-AGENT REINFORCEMENT LEARNING Q-LEARNING