gym online with Winfy

We have hosted the application gym in order to run this application in our online workstations with Wine or directly.

Quick description about gym:

Gym 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 assumptions about the structure of your agent, and is compatible with any numerical computation library, such as TensorFlow or Theano. The gym library is a collection of test problems � environments � that you can use to work out your reinforcement learning algorithms. These environments have a shared interface, allowing you to write general algorithms.

Features:

• Develop and compare reinforcement learning algorithms
• Simple suite library of reinforcement learning tasks
• Write algorithms using your numerical computation library of choice
• Learn to imitate computations and control theory problems
• Make 2D and 3D simulation models
• Make models that perform simulated goal-based tasks

Programming Language: Python.
Categories: