uber-research

Deep Neuroevolution

Plug and Play Language Model implementation. Allows to steer topic and attributes of GPT-2 models.

UPSNet: A Unified Panoptic Segmentation Network

Code for Go-Explore: a New Approach for Hard-Exploration Problems

[ECCV2020 Oral] Learning Lane Graph Representations for Motion Forecasting

Sparse Blocks Networks

Implementations of the algorithms described in Differentiable plasticity: training plastic networks with gradient descent, a research paper from Uber AI Labs.

DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatch (ICCV 2019)

Tool for interactive embeddings visualization

Code for paper "Learning to Reweight Examples for Robust Deep Learning"

Paired Open-Ended Trailblazer (POET) and Enhanced POET

A binary release of trained deep reinforcement learning models trained in the Atari machine learning benchmark, and a software release that enables easy visualization and analysis of models, and...

This repo replicates the results Horgan et al obtained in "Distributed Prioritized Experience Replay"

Using ideas from product quantization for state-of-the-art neural network compression.

safemutations

Train self-modifying neural networks with neuromodulated plasticity

Uber's Multi-Agent Routing Value Iteration Network