group controller
Integrating Suboptimal Human Knowledge with Hierarchical Reinforcement Learning for Large-Scale Multiagent Systems
While agents' learning is data-driven, sampling from millions
Integrating Suboptimal Human Knowledge with Hierarchical Reinforcement Learning for Large-Scale Multiagent Systems
While agents' learning is data-driven, sampling from millions
SuperPADL: Scaling Language-Directed Physics-Based Control with Progressive Supervised Distillation
Juravsky, Jordan, Guo, Yunrong, Fidler, Sanja, Peng, Xue Bin
Physically-simulated models for human motion can generate high-quality responsive character animations, often in real-time. Natural language serves as a flexible interface for controlling these models, allowing expert and non-expert users to quickly create and edit their animations. Many recent physics-based animation methods, including those that use text interfaces, train control policies using reinforcement learning (RL). However, scaling these methods beyond several hundred motions has remained challenging. Meanwhile, kinematic animation models are able to successfully learn from thousands of diverse motions by leveraging supervised learning methods. Inspired by these successes, in this work we introduce SuperPADL, a scalable framework for physics-based text-to-motion that leverages both RL and supervised learning to train controllers on thousands of diverse motion clips. SuperPADL is trained in stages using progressive distillation, starting with a large number of specialized experts using RL. These experts are then iteratively distilled into larger, more robust policies using a combination of reinforcement learning and supervised learning. Our final SuperPADL controller is trained on a dataset containing over 5000 skills and runs in real time on a consumer GPU. Moreover, our policy can naturally transition between skills, allowing for users to interactively craft multi-stage animations. We experimentally demonstrate that SuperPADL significantly outperforms RL-based baselines at this large data scale.
Webinar: A pragmatic approach to robotics and ai in financial management - Stora Enso & Aitomation
Petra Terasaho works as Stora Enso Group Controller since February 2016. The responsibilities are Group Accounting & Reporting, Group Business Controlling, Internal Controls, Financial Shared Service Center, Finance tools, processes & policies. During the past two years Petra has specialized in finance digitalization, robotics, AI solutions, Advanced Data Analytics and how these changes will impact the finance organization. Petra is driving a big finance transformation and digitalization currently. Prior to Stora Enso Petra worked as Group Controller at Outotec.