uber-research/go-explore

This repository has been archived on 05/Jan/2024
Stars
553
Rank 80,462 (Top 2 %)
Language
Python
License
Other
Created almost 6 years ago
Updated almost 2 years ago

uber-research/go-explore

uber-research

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

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

Go-Explore

This is the code for First return then explore, the new Go-explore paper. Code for the original paper can be found in this repository under the tag "v1.0" or the release "Go-Explore v1".

The code for Go-Explore with a deterministic exploration phase followed by a robustification phase is located in the robustified subdirectory. The code for Go-Explore with a policy-based exploration phase is located in the policy_based subdirectory. Installation instructions for each variant of Go-Explore can be found in their respective directories.

deep-neuroevolution

Deep Neuroevolution

PPLM

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

UPSNet

UPSNet: A Unified Panoptic Segmentation Network

PyTorch-NEAT

LaneGCN

[ECCV2020 Oral] Learning Lane Graph Representations for Motion Forecasting

sbnet

Sparse Blocks Networks

differentiable-plasticity

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

DeepPruner

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

parallax

Tool for interactive embeddings visualization

learning-to-reweight-examples

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

jpeg2dct

poet

Paired Open-Ended Trailblazer (POET) and Enhanced POET

intrinsic-dimension

Jupyter Notebook

CoordConv

atari-model-zoo

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 comparison across training algorithms.

Jupyter Notebook

ape-x

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

EvoGrad

TuRBO

safemutations

permute-quantize-finetune

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

deconstructing-lottery-tickets

CRISP

metropolis-hastings-gans

GTN

backpropamine

Train self-modifying neural networks with neuromodulated plasticity

loss-change-allocation

MARVIN

Uber's Multi-Agent Routing Value Iteration Network

GOCC

Synthetic-Petri-Dish

RxThreadEffectChecker

Static checker for Rx Threading Effects, based on the Checker Framework

Map-Elites-Evolutionary

Map-Elites based on Evolution Strategies

D3G

Estimating Q(s,s') with Deep Deterministic Dynamics Gradients

java-dependency-validator

Dependency validator detects runtime compatibility issues at build time

vargp

Variational Auto-Regressive Gaussian Processes for Continual Learning

normative-uncertainty

Evolvability-ES

brezel

dispatch-optim

Constrainted based optimization

ga-world-models

FSDM

Code tor the SIGDIAL 2019 paper Flexibly-Structured Model for Task-Oriented Dialogues. It implements a deep learning end-to-end differentiable dialogue system model

rl-controller-verification

Quadcopter Verification

go-context-propagate

last-diff-analyzer

A multi-language tool for checking semantic equivalence for code

presto-HDFS-read-data

A dump of some of our Presto logs, for use as part of ongoing Presto/HDFS research and presentations.

xplane-bazel-docker

tailr