Fixes * UnityEnvironment no longer uses OS-specific `signal.alarm` to timeout connection with Unity. (https://github.com/Unity-Technologies/ml-agents/pull/9) Changes * PPO now allows for saving more than the most 5 recent model checkpoints. (https://github.com/Unity-Technologies/ml-agents/pull/16)
0.1
Unity Machine Learning Agents allows researchers and developers to create games and simulations using the Unity Editor into environments where intelligent agents can be trained using reinforcement learning, evolutionary strategies, or other machine learning methods through a simple to use Python API.