AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control
TLDR
In this paper, an adversarial RL procedure automatically selects which motion to perform, dynamically interpolating and generalizing from the dataset, without requiring a high-level motion planner or other task-specific annotations of the motion clips.Abstract:
Synthesizing graceful and life-like behaviors for physically simulated characters has been a fundamental challenge in computer animation. Data-driven methods that leverage motion tracking are a prominent class of techniques for producing high fidelity motions for a wide range of behaviors. However, the effectiveness of these tracking-based methods often hinges on carefully designed objective functions, and when applied to large and diverse motion datasets, these methods require significant additional machinery to select the appropriate motion for the character to track in a given scenario. In this work, we propose to obviate the need to manually design imitation objectives and mechanisms for motion selection by utilizing a fully automated approach based on adversarial imitation learning. High-level task objectives that the character should perform can be specified by relatively simple reward functions, while the low-level style of the character's behaviors can be specified by a dataset of unstructured motion clips, without any explicit clip selection or sequencing. These motion clips are used to train an adversarial motion prior, which specifies style-rewards for training the character through reinforcement learning (RL). The adversarial RL procedure automatically selects which motion to perform, dynamically interpolating and generalizing from the dataset. Our system produces high-quality motions that are comparable to those achieved by state-of-the-art tracking-based techniques, while also being able to easily accommodate large datasets of unstructured motion clips. Composition of disparate skills emerges automatically from the motion prior, without requiring a high-level motion planner or other task-specific annotations of the motion clips. We demonstrate the effectiveness of our framework on a diverse cast of complex simulated characters and a challenging suite of motor control tasks.read more
Citations
More filters
Proceedings ArticleDOI
Dataset Distillation by Matching Training Trajectories
TL;DR: This paper proposes a new formulation that optimizes the authors' distilled data to guide networks to a similar state as those trained on real data across many training steps, and handily outperforms existing methods and also allows us to distill higher-resolution visual data.
Journal ArticleDOI
ASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated Characters
TL;DR: This work presents a large-scale data-driven framework for learning versatile and reusable skill embeddings for physically simulated characters, and shows that a single pre-trained model can be effectively applied to perform a diverse set of new tasks.
Proceedings ArticleDOI
Behavior Transformers: Cloning k modes with one stone
TL;DR: Behavior Transformer is presented, a new technique to model unlabeled demonstration data with multiple modes and improves over prior state-of-the-art work on solving demonstrated tasks while capturing the major modes present in the pre-collected datasets.
Proceedings ArticleDOI
Accelerated Policy Learning with Parallel Differentiable Simulation
Jie Xu,Viktor Makoviychuk,Yashraj S. Narang,Fabio Ramos,Wojciech Matusik,Animesh Garg,Miles Macklin +6 more
TL;DR: A high-performance differentiable simulator and a new policy learning algorithm (SHAC) that can effectively leverage simulation gradients, even in the presence of non-smoothness are presented.
Journal ArticleDOI
DeepPhase: periodic autoencoders for learning motion phase manifolds
Sebastian Starke,Ian A. Mason,Taku Komura,Zhaoming Xie,Michiel van de Panne,Yiwei Zhao,Fabio Zinno +6 more
TL;DR: It is demonstrated that the learned periodic embedding can significantly help to improve neural motion synthesis in a number of tasks, including diverse locomotion skills, style-based move- ments, dance motion synthesis from music, synthesis of dribbling motions in football, and motion query for matching poses within large animation databases.
References
More filters
Journal ArticleDOI
Generative Adversarial Nets
Ian Goodfellow,Jean Pouget-Abadie,Mehdi Mirza,Bing Xu,David Warde-Farley,Sherjil Ozair,Aaron Courville,Yoshua Bengio +7 more
TL;DR: A new framework for estimating generative models via an adversarial process, in which two models are simultaneously train: a generative model G that captures the data distribution and a discriminative model D that estimates the probability that a sample came from the training data rather than G.
Proceedings Article
Auto-Encoding Variational Bayes
Diederik P. Kingma,Max Welling +1 more
TL;DR: A stochastic variational inference and learning algorithm that scales to large datasets and, under some mild differentiability conditions, even works in the intractable case is introduced.
Proceedings Article
Rectified Linear Units Improve Restricted Boltzmann Machines
Vinod Nair,Geoffrey E. Hinton +1 more
TL;DR: Restricted Boltzmann machines were developed using binary stochastic hidden units that learn features that are better for object recognition on the NORB dataset and face verification on the Labeled Faces in the Wild dataset.
Posted Content
Proximal Policy Optimization Algorithms
TL;DR: A new family of policy gradient methods for reinforcement learning, which alternate between sampling data through interaction with the environment, and optimizing a "surrogate" objective function using stochastic gradient ascent, are proposed.
Book
Introduction to Reinforcement Learning
TL;DR: In Reinforcement Learning, Richard Sutton and Andrew Barto provide a clear and simple account of the key ideas and algorithms of reinforcement learning.