To control the behavior of physics-based characters through language, Nvidia's PADL combines a language model with reinforcement learning. One thing that comes to mind when remembering the start of this wave of AI is certainly the strangely moving 3D figures from Deepmind and other research institutions. These three-legged spiders or humanoid 3D puppets had learned their movements through reinforcement learning. There are now numerous approaches to making digital animals or human-like figures learn movements on their own. The goal of these methods is to develop AI systems that can generate natural-looking movements for a variety of simulated figures and thus complement or replace manual animation and motion capture processes in the long term.

Developing systems that can synthesize natural and life-like motions for simulated characters has long been a focus for computer animation. But in order for these systems to be useful for downstream applications, they need not only produce high-quality motions, but must also provide an accessible and versatile interface through which users can direct a character's behaviors. Natural language provides a simple-to-use and expressive medium for specifying a user's intent. Recent breakthroughs in natural language processing (NLP) have demonstrated effective use of language-based interfaces for applications such as image generation and program synthesis. In this work, we present PADL, which leverages recent innovations in NLP in order to take steps towards developing language-directed controllers for physics-based character animation. PADL allows users to issue natural language commands for specifying both high-level tasks and low-level skills that a character should perform. We present an adversarial imitation learning approach for training policies to map high-level language commands to low-level controls that enable a character to perform the desired task and skill specified by a user's commands. Furthermore, we propose a multi-task aggregation method that leverages a language-based multiple-choice question-answering approach to determine high-level task objectives from language commands. We show that our framework can be applied to effectively direct a simulated humanoid character to perform a diverse array of complex motor skills.

Programs are read more often than they are written. Models are used more often than they are trained. The PyTorch, and the deep-learning ecosystem in general, abounds with tools for training models, and squeezing the best performance out of computational resources in doing this. In the life cycle of a model this is only the beginning of the journey. Once a model has been trained, it will be shared, and used in a multitude of contexts, often on a daily basis, in operations, evaluation, comparision and experimentation by data scientists.

You've spent a few days with sweat and tears putting together a PyTorch model in a Jupyter notebook, tinkering with parameters, trying various preprocessing methods, post-processing methods, validating the model results on examples, and checking on validation data sets that the model performs well. The results are good, you're happy, your boss (if you have one) and colleagues are happy. Now you'd like to share the results, so that other people can play with the model; so what do you do? None of these are ideal. It doesn't have to be this way… In this blog post we discuss how to use PADL around an NLP code example.