zmonoid / mxasyn
Asynchronous One Step Q Learning implemented with MXNET
☆20Updated 7 years ago
Related projects ⓘ
Alternatives and complementary repositories for mxasyn
- MXNet implementation of Deep Q-learning☆34Updated 6 years ago
- Deterministic Policy Gradient using torch7☆44Updated 8 years ago
- Asynchronous Advantage Actor Critic☆21Updated 8 years ago
- Universal library for deep reinforcement learning.☆39Updated 8 years ago
- miniplaces2 deep residual network in neon☆16Updated 8 years ago
- Torch implementation reproducing MNIST experiments from DeepMind's DNI paper.☆44Updated 7 years ago
- Deep reinforcement learning package for torch7☆16Updated 8 years ago
- DNI(Decoupled Neural Interfaces using Synthetic Gradients) implementation with Torch☆29Updated 8 years ago
- Implementation of a simple example of Q learning in Torch.☆50Updated 7 years ago
- Atari gauntlet for RL agents☆29Updated 7 years ago
- Benchmarking different LSTM libraries☆24Updated 8 years ago
- reinfore learning tool box, contains trpo, a3c algorithm for continous action space☆43Updated 6 years ago
- Tensorflow Implementation of Multi-Function Recurrent Unit☆24Updated 8 years ago
- Experimentation with Highway Networks & GradNets☆13Updated 8 years ago
- Torch implementation of the Deep Network for Global Optimization (DNGO)☆51Updated 8 years ago
- Collection of reinforcement learners implemented in python. Mainly including DQN and its variants☆54Updated 7 years ago
- Playground for some RNN stuff in Torch.☆20Updated 9 years ago
- ☆19Updated 8 years ago
- an updated version of fb.resnet.torch with many changes.☆37Updated 7 years ago
- Sublinear memory optimization for deep learning, reduce GPU memory cost to train deeper nets☆29Updated 8 years ago
- ☆32Updated 8 years ago
- Flattened convolutional neural networks (1D convolution modules for Torch nn)☆61Updated 9 years ago