Train and embed intelligent agents by leveraging state-of-the-art deep learning technology. Creating responsive and intelligent virtual players and non-playable game characters is hard. Especially when the game is complex. To create intelligent behaviors, developers have had to resort to writing tons of code or using highly specialized tools. With Unity Machine Learning Agents (ML-Agents), you are no longer “coding” emergent behaviors, but rather teaching intelligent agents to “learn” through a combination of deep reinforcement learning and imitation learning. ...
A platform for rapid Reinforcement Learning methods development
Application allowing convenient experimentation in Reinforcement Learning - a Machine Learning domain. Project goals are:
- keep adding new environments and agents as simple as possible
- provide a rich set of state-of-art algorithms and problems
- integrate with other existing Reinforcement Learning platforms
If you found this application useful please cite this work: http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6643987