Topic: imitation learning

Yejin Choi examines how data diversity, synthetic examples, imitation learning and reinforcement learning can strengthen reasoning in small language models. The conversation discusses output homogeneity, Prismatic Synthesis, training models to reason before predicting tokens, and pluralistic alignment that represents a broader range of human values.

Nikita Rudin discusses reinforcement learning for robot locomotion and the difficulties of transferring policies from simulation to physical robots. Topics include visual inputs, real-world data for improving simulators, imitation learning and teleoperation, hierarchical control, and trade-offs between modular and end-to-end approaches for autonomous robots.

Developing agents capable of modeling complex environments and human behaviors within them is a key goal of artificial intelligence research. Progress towards this goal has exciting potential for applications in video games, from new tools that empower game developers to realize new creative visions, to enabling new kinds of immersive player experiences. This talk focuses on recent advances of my team at Microsoft Research towards scalable machine learning architectures that effectively capture human gameplay data. In the first part of my talk, I will focus on diffusion models as generative mo

Developing agents capable of modeling complex environments and human behaviors within them is a key goal of artificial intelligence research. Progress towards this goal has exciting potential for applications in video games, from new tools that empower game developers to realize new creative visions, to enabling new kinds of immersive player experiences. This talk focuses on recent advances of my team at Microsoft Research towards scalable machine learning architectures that effectively capture human gameplay data. In the first part of my talk, I will focus on diffusion models as generative mo