Toolkit for developing and comparing reinforcement learning algorithms
Gym by OpenAI is a toolkit for developing and comparing reinforcement learning algorithms. It supports teaching agents, everything from walking to playing games like Pong or Pinball. Open source interface to reinforce learning tasks. The gym library provides an easy-to-use suite of reinforcement learning tasks. Gym provides the environment, you provide the algorithm. You can write your agent using your existing numerical computation library, such as TensorFlow or Theano. It makes no...
a very lightweight advanced terrain-rendering and 3D map rendering sys
A very lightweight advanced terrain-rendering and 3D map rendering system. Minimal dependencies: OpenGL, SDL.
It's distrib in 2-3 separate modules:
1. the C++ implementation of the terrain- and/or surface- rendering Algorithms I have developed: both a multithread and a non-multithread variant is relaeased.
2. Seme as at point 1. , but with a road-network rendering and collision-detection module I wrote before. It also adds some trees at the top of the terrain. (multitread vesion not...