Stars
Simplifying reinforcement learning for complex game environments
Automatically exported from code.google.com/p/v-hacd
This is a library that provides dual dexterous hand manipulation tasks through Isaac Gym
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
An pytorch implementation of time-contrastive networks as presented in the paper "Time-Contrastive Networks: Self-Supervised Learning from Multi-View Observation".
Tensorflow implementation of Magnet Loss from "Metric Learning for Adaptive Density Discrimination"
Implementation of VLAE
Direct Future Prediction (DFP ) in Keras
Efficient Batched Reinforcement Learning in TensorFlow
Initial commit. Tensorboard running with embeddings to utilise t-SNE
OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
Accompanying repository for Let's make a DQN / A3C series.
Domain-Adversarial Neural Network in Tensorflow
Keras Implementation of Neural Style Transfer from the paper "A Neural Algorithm of Artistic Style" (http://arxiv.org/abs/1508.06576) in Keras 2.0+
Code for reproducing key results in the paper "InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets"
Code for reproducing key results in the paper "Improving Variational Inference with Inverse Autoregressive Flow"
Code for the paper "Generative Adversarial Imitation Learning"
Project Malmo is a platform for Artificial Intelligence experimentation and research built on top of Minecraft. We aim to inspire a new generation of research into challenging new problems presente…
rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.
Warehouse for running small experiments and sharing them with the group
A Neural Net Training Interface on TensorFlow, with focus on speed + flexibility