Pinned Loading

1. distance distance Public

   Reinforcement learning project. The objective is to learn an asymmetric distance function over states that will allow goal-pursuing.

   Python

2. wgan-exploration wgan-exploration Public

   RL Project. Use absolute value of WGAN critic score as intrinsic reward for PPO agent to achieve deep exploration in sparse reward environments.

   Python

3. cuda-conv2d cuda-conv2d Public

   A simple (work-in-progress) implementation of 2d convolution using CUDA.

   Cuda 1

4. ppo ppo Public

   A simple implementation of PPO, tested on CartPole and Pong and Space Invaders (so far).

   Python

5. dadsite dadsite Public

   scottjohnstonportraits.com website. Uses Django, lots of javascript and css to look good at many window sizes

   HTML

6. evolution evolution Public

   Reproduction of "Deep Neuroevolution: Genetic Algorithms are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning": https://arxiv.org/pdf/1712.06567.pdf

   Python 1