Over the past several years, games and simulations have become a powerful tool for AI research. They have become the default testing grounds for new algorithms thanks to platforms such as Mujoco, Arcade Learning Environment, OpenAI Gym, VizDoom, DeepMind Lab, Facebook House3D, Allen Institute AI2-Thor, Microsoft AirSim, General Video Game AI and Unity ML-Agents toolkit. Additionally, they are a mechanism for generating large amounts of training data for learning complex models for tasks such as 3D pose estimation, physics modeling, natural language instruction following, embodied question answering and robotics. Due to the physical and visual realism of several of these platforms, complex models can be trained in a virtual setting and then transferred to an agent or robot in the real world with minor fine-tuning. Recent examples include learning dexterous manipulation behaviors for a robotic hand and training self-driving cars.
We were excited to organize the AAAI-2019 Workshop on Games and Simulations for Artificial Intelligence on January 28, 2019. It was a full-day workshop that included a mix of invited speakers and peer-reviewed papers (talks and poster sessions).
Thank you to all those who attended and made the workshop a fantastic event.
Marwan, Roozbeh, Julian and Danny