Imitation learning

…extended action sequences improved imitation learning and subsequently offline and offline-to-online reinforcement learning. It reviews algorithms built around these representations and large-scale control models that use them, connecting policy expressiveness with practical learning performance.

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.

…Moreover, imitation learning theories of aggression suggest that this behavior can be transferred through observation alone1, but whether this learning leverages the same neural mechanisms as experience is unclear. To address these two questions, here we combine novel behavioral mapping strategies with cell-type-specific and mu

Many behaviors demand a balance between exploitation, which requires reliability, and exploration, which involves flexibility. In cortical circuits, much work has emphasized how attractor dynamics generate reliable behavior through the convergence of a network to specialized activity patterns for specific decisions and actions1. Other work has emphasized how cortical activity exhibits variability across trials of a behavior, which could in principle support flexibility in actions2. Here, through multi-area calcium imaging and recurrent neural network models, we propose that cortical activity f

…the potential of deep reinforcement learning to capture sensorimotor representations. By training artificial agents to imitate natural grasp movements using imitation learning, we develop stimul

…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

…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