pathak22 Goto Github PK

baselines

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

caffe-ccnn

Branch of caffe for weakly supervised learning.

ccnn

[ICCV 2015] Framework for optimizing CNNs with linear constraints for Semantic Segmentation

context-encoder

[CVPR 2016] Unsupervised Feature Learning by Image Inpainting using GANs

corr_clustering

Correlation Clustering Project

dreamer

Dream to Control: Learning Behaviors by Latent Imagination

exploration-by-disagreement

[ICML 2019] TensorFlow Code for Self-Supervised Exploration via Disagreement

gym-pull

Add-on for OpenAI Gym that supports automatic downloading of user environments.

hierarchical-imitation

[NeurIPS 2019] Code for Hierarchical Third-Person Imitation Learning

large-scale-curiosity-1

Code for the paper "Large-Scale Study of Curiosity-Driven Learning"

modular-assemblies

[NeurIPS 2019] Code for the paper "Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity"

noreward-rl

[ICML 2017] TensorFlow code for Curiosity-driven Exploration for Deep Reinforcement Learning

pathak22.github.io

pyflow

Fast, accurate and easy to run dense optical flow with python wrapper

seg-by-interaction

Unsupervised instance segmentation via active robot interaction

unsupervised-video

[CVPR 2017] Unsupervised deep learning using unlabelled videos on the web

videoseg

[CVPR 2017] Video motion segmentation and tracking

zeroshot-imitation

[ICLR 2018] TensorFlow code for zero-shot visual imitation by self-supervised exploration