Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

awesome-deep-reinforcement-learning

Curated list for Deep Reinforcement Learning (DRL): software frameworks, models, datasets, gyms, baselines...
https://github.com/jgvictores/awesome-deep-reinforcement-learning

Last synced: 2 days ago
JSON representation

  • Neural Networks (NN) and Deep Neural Networks (DNN)

    • NN/DNN Datasets

    • NN/DNN Pretrained Models

      • keras web - team/keras/tree/master/keras/applications), [keras 2](https://github.com/keras-team/keras-applications), [pytorch](https://pytorch.org/docs/stable/torchvision/models.html), [caffe](https://github.com/BVLC/caffe/wiki/Model-Zoo), [ONNX](https://github.com/onnx/models) (pytorch/caffe2).
      • keras
      • keras by keras - team/keras/tree/e15533e6c725dca8c37a861aacb13ef149789433/keras/applications)) / [keras by kaggle](https://www.kaggle.com/keras) / [pytorch by kaggle](https://www.kaggle.com/pytorch)
      • keras
      • keras
      • caffe by original VGG author
      • gensim
    • NN/DNN Techniques Misc

    • NN/DNN Visualization and Explanation

      • keras - deep-learning-neural-network-model-keras/), [2](https://github.com/keplr-io/quiver), [3](https://raghakot.github.io/keras-vis/), [4](https://www.kaggle.com/amarjeet007/visualize-cnn-with-keras)
      • tensorboard
    • NN/DNN Software Frameworks

      • presentation - deep-reinforcement-learning/blob/143a885cc10b4331b9b3fa3e1a9436d5325676af/doc/inria2017DLFrameworks.pdf)).
      • safari
      • safari
      • 1
      • DALI - accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.
      • Sonnet
      • ml5
      • Torch
      • CoreML - C) (support: Apple)
      • OpenNN
      • Caffe
      • 1 - docker), [3](https://github.com/bethgelab/docker-deeplearning).
      • 1
      • pytorch/pytorch - commit/pytorch/pytorch?label=last%20update)
      • keras-team/keras - team/keras)](https://github.com/keras-team/keras/stargazers) ![GitHub last commit](https://img.shields.io/github/last-commit/keras-team/keras?label=last%20update)
      • tensorflow/tensorflow - level) (API: Python most stable, JavaScript, C++, Java...) (support: Google). [![GitHub stars](https://img.shields.io/github/stars/tensorflow/tensorflow)](https://github.com/tensorflow/tensorflow/stargazers) ![GitHub last commit](https://img.shields.io/github/last-commit/tensorflow/tensorflow?label=last%20update)
      • flashlight/flashlight - commit/flashlight/flashlight?label=last%20update)
      • https://github.com/janhuenermann/neurojs - commit/janhuenermann/neurojs?label=last%20update)
      • 1
      • 1
      • oneapi-src/oneDNN
      • sony/nnabla
      • 1
      • jittor
      • PaddlePaddle
      • GitHub
      • GitHub
      • GitHub
      • DL4J
      • GitHub
      • PyBrain
    • NN/DNN Models

      • 1
      • arxiv - fcis).
      • arxiv - freiburg.de/people/ronneber/u-net/).
      • arxiv
      • arxiv - Single-Shot-MultiBox-Detector)
      • arxiv
      • arxiv - brief-history-of-cnns-in-image-segmentation-from-r-cnn-to-mask-r-cnn-34ea83205de4)): Fast R-CNN, Faster R-CNN, Mask R-CNN.
      • 1 - tricks.com/cnn/understand-resnet-alexnet-vgg-inception/), [3](https://medium.com/@sidereal/cnns-architectures-lenet-alexnet-vgg-googlenet-resnet-and-more-666091488df5)
      • arxiv
      • arxiv
      • arxiv
      • arxiv
      • arxiv - 3 weeks.
      • arxiv - 7 million parameters, via smaller convs. A more aggressive cropping approach than that of Krizhevsky. Batch normalization, image distortions, RMSprop. Uses 9 novel "Inception modules" (at each layer of a traditional ConvNet, you have to make a choice of whether to have a pooling operation or a conv operation as well as the choice of filter size; an Inception module performa all these operations in parallel), and no fully connected. Trained on CPU (estimated as weeks via GPU) implemented in DistBelief (closed-source predecessor of TensorFlow). Variants ([summary](https://towardsdatascience.com/a-simple-guide-to-the-versions-of-the-inception-network-7fc52b863202)): v1, v2, v4, resnet v1, resnet v2; v9 ([slides](http://lsun.cs.princeton.edu/slides/Christian.pdf)). Also see [Xception (2017)](https://arxiv.org/pdf/1610.02357.pdf) paper.
      • arxiv
      • doi - justified finer tuning and visualization (namely Deconvolutional Network).
      • doi
      • Geometric deep learning
      • ref
      • tensorflow
      • arxiv - painterly-harmonization)
      • arxiv - photo-styletransfer)
      • arxiv - style), keras [1](https://github.com/keras-team/keras/blob/master/examples/neural_style_transfer.py) [2](https://github.com/titu1994/Neural-Style-Transfer) [3](https://github.com/handong1587/handong1587.github.io/blob/master/_posts/deep_learning/2015-10-09-fun-with-deep-learning.md) [4](https://medium.com/mlreview/making-ai-art-with-style-transfer-using-keras-8bb5fa44b216)
      • arxiv - pytorch)
      • arxiv
      • arxiv - Adversarial-Networks)
      • arxiv
      • arxiv
      • FTTNet - Time Speaker-Dependent Neural Vocoder". [pytorch](https://github.com/mozilla/FFTNet)
      • keras
      • keras - image-similarity)
      • arxiv
      • wikipedia
      • 1
      • ref
      • 1
      • 1
      • facebookresearch/Detectron
      • thunlp/GNNPapers
      • chihming/awesome-network-embedding
      • DLG
      • pytorch
      • tensorflow/gnn
      • pytorch
      • ref
      • caffe
      • hindupuravinash/the-gan-zoo
      • CycleGAN - Yan Zhu et Al; Berkeley; "Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks". [torch](https://github.com/junyanz/CycleGAN) and migrated to [pytorch](https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix).
      • 1
      • ref
      • 1
      • ref
      • 1
      • 1
      • ref
      • 1
      • 1
      • ref
      • 1
      • ref
      • 1
      • ref
      • 1
      • 1
      • 1
      • doi
      • ref
      • 1
      • ref
      • 1
      • facebookresearch/Detectron
      • 1
      • 1
      • 1
      • ref
      • 1
      • 1
      • 1
      • 1
      • 1
      • 1
      • 1
      • ref
      • 1
      • 1
      • ref
      • 1
      • 1
      • ref
      • 1
      • 1
      • 1
      • 1
      • 1
      • ref
      • 1
      • 1
      • 1
      • 1
      • 1
      • 1
      • 1
      • 1
      • 1
      • 1
      • 1
      • 1
      • ref
      • 1
      • ref
      • 1
      • ref
      • 1
      • 1
      • 1
      • 1
      • 1
      • doi - 61 million parameters, split into 2 pipelines to enable 5-6 day GTX 580 GPU training (while CPU data augmentation).
      • 1
      • 1
      • 1
      • 1
      • ref
      • 1
      • 1
      • ref
      • ref
      • 1
  • Reinforcement Learning (RL) and Deep Reinforcement Learning (DRL)

    • RL/DRL Algorithms

    • RL/DRL Algorithm Implementations and Software Frameworks

      • RL-Glue - glue-ext/wikis/RLGlueCore.wiki)) (API: C/C++, Java, Matlab, Python, Lisp) (support: Alberta)
  • Similar pages

  • General Machine Learning (ML)