Our latest, stable release is Release 20. See our ML-Agents Overview page for detailedĭescriptions of all these features. Wrap Unity learning environments as a PettingZoo environment.
Support for learning from demonstrations through two Imitation Learning algorithms (BC and GAIL).Support for training single-agent, multi-agent cooperative, and multi-agentĬompetitive scenarios via several Deep Reinforcement Learning algorithms (PPO, SAC, MA-POCA, self-play).Flexible Unity SDK that can be integrated into your game or custom Unity scene.Support for multiple environment configurations and training scenarios.Rich environments and then made accessible to the wider research and game Provides a central platform where advances in AI can be evaluated on Unity’s Toolkit is mutually beneficial for both game developers and AI researchers as it Settings such as multi-agent and adversarial), automated testing of game buildsĪnd evaluating different game design decisions pre-release. Used for multiple purposes, including controlling NPC behavior (in a variety of Imitation learning, neuroevolution, or any other methods. Provided simple-to-use Python API to train Agents using reinforcement learning, Train intelligent agents for 2D, 3D and VR/AR games. Of state-of-the-art algorithms to enable game developers and hobbyists to easily We provide implementations (based on PyTorch) Project that enables games and simulations to serve as environments for The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source
0 kommentar(er)
