aistrych's repositories
rllab
rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.
reinforcement-learning
Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.
RecurrentHighwayNetworks
Recurrent Highway Networks - Implementations for Tensorflow, Torch7, Theano and Brainstorm
keras-rl
Deep Reinforcement Learning for Keras.
residual_block_keras
Residual network block in Keras
A3C
Advantage async actor-critic Algorithms (A3C) and Progressive Neural Network implemented by tensorflow.
tensorflow_with_latest_papers
Implementation of Newest RNN and Seq2Seq Features
tf-agent
tensorflow reinforcement learning agents for OpenAI gym environments
DNI-tensorflow
DNI(Decoupled Neural Interfaces using Synthetic Gradients) implementation with Tensorflow
Atari
Persistent advantage learning dueling double DQN for the Arcade Learning Environment
ufcnn-keras
Implementation of UFCNN in Keras
async_deep_reinforce
Asynchronous Methods for Deep Reinforcement Learning
highway-fcn
Simple fully-connected highway networks using TensorFlow and Fomoro.
highway-cnn
Simple convolutional highway networks using TensorFlow and Fomoro.
deep_trader
This project uses reinforcement learning on stock market and agent tries to learn trading. The goal is to check if the agent can learn to read tape. The project is dedicated to hero in life great Jesse Livermore.
ufcnn
Implementation of Undecimated Fully Convolutional Neural Network for time series modeling
keras-resnet
Residual networks implementation using Keras-1.0 functional API
async_deep_reinforce-1
A3C implementation which trains an agent for a small MDP.
RAM
"Recurrent Models of Visual Attention" in TensorFlow
snli-entailment
attention model for entailment on SNLI corpus
async-rl
Tensorflow + Keras + OpenAI Gym implementation of 1-step Q Learning from "Asynchronous Methods for Deep Reinforcement Learning"
genstake-newer
Genstake - fork for historic purposes ;)
Associative_LSTM
LSTM with associative memory cells (http://arxiv.org/abs/1602.03032)
Asynchronous-Methods-for-Deep-Reinforcement-Learning
Using a paper from Google DeepMind I've developed a new version of the DQN using threads exploration instead of memory replay as explain in here: http://arxiv.org/pdf/1602.01783v1.pdf I used the one-step-Q-learning pseudocode, and now we can train the Pong game in less than 20 hours and without any GPU or network distribution.
resnet-tf
ResNet Implementation in TensorFlow
DARQN
Deep Attention Recurrent Q-Network
DropoutUncertaintyDemos
What My Deep Model Doesn't Know...
highway-networks
An implementation of Highway Networks in Caffe