Session Name: | Unity for Deep Learning: ML-Agents Explained (Presented by Unity Technologies) |
Speaker(s): | Mike Geig, Arthur Juliani |
Company Name(s): | Unity Technologies, Unity Technologies |
Track / Format: | Programming |
Overview: | Unity is building a new generation of tools to empower game developers with techniques from modern machine learning. Presenters will walk through recent developments in Deep Reinforcement Learning, and show how they can be applied to the development and testing of in-game AI using ML-Agents, a new open-source toolkit built to enable training and deploying Deep Learning models within Unity. In addition to walking through the current features of ML-Agents, presenters will also demonstrate new features which enable training agents using only human demonstrations, as well as training many agents within a single scene. |