907 citations · 1.3k across the 17 of their papers we have counts for
17 papers
CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control
Guy Tevet, Sigal Raab, Setareh Cohan +5
Motion diffusion models and Reinforcement Learning (RL) based control for physics-based simulations have complementary strengths for human motion generation. The former is capable…
Flexible Motion In-betweening with Diffusion Models
Setareh Cohan, Guy Tevet, Daniele Reda +2
Motion in-betweening, a fundamental task in character animation, consists of generating motion sequences that plausibly interpolate user-provided keyframe constraints. It has long…
Physics-based Motion Retargeting from Sparse Inputs
Daniele Reda, Jungdam Won, Yuting Ye +2
Avatars are important to create interactive and immersive experiences in virtual worlds. One challenge in animating these characters to mimic a user's motion is that commercial AR/…
Evaluating Vision Transformer Methods for Deep Reinforcement Learning from Pixels
Tianxin Tao, Daniele Reda, Michiel van de Panne
Vision Transformers (ViT) have recently demonstrated the significant potential of transformer architectures for computer vision. To what extent can image-based deep reinforcement l…
Learning to Brachiate via Simplified Model Imitation
Daniele Reda, Hung Yu Ling, Michiel van de Panne
Brachiation is the primary form of locomotion for gibbons and siamangs, in which these primates swing from tree limb to tree limb using only their arms. It is challenging to contro…
Exploration with Multi-Sample Target Values for Distributional Reinforcement Learning
Michael Teng, Michiel van de Panne, Frank Wood
Distributional reinforcement learning (RL) aims to learn a value-network that predicts the full distribution of the returns for a given state, often modeled via a quantile-based cr…
From Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligence
Nicholas Roy, Ingmar Posner, Tim Barfoot +17
Machine learning has long since become a keystone technology, accelerating science and applications in a broad range of domains. Consequently, the notion of applying learning metho…
Discovering Diverse Athletic Jumping Strategies
Zhiqi Yin, Zeshi Yang, Michiel van de Panne +1
We present a framework that enables the discovery of diverse and natural-looking motion strategies for athletic skills such as the high jump. The strategies are realized as control…
GLiDE: Generalizable Quadrupedal Locomotion in Diverse Environments with a Centroidal Model
Zhaoming Xie, Xingye Da, Buck Babich +2
Model-free reinforcement learning (RL) for legged locomotion commonly relies on a physics simulator that can accurately predict the behaviors of every degree of freedom of the robo…
Character Controllers Using Motion VAEs
Hung Yu Ling, Fabio Zinno, George Cheng +1
A fundamental problem in computer animation is that of realizing purposeful and realistic human movement given a sufficiently-rich set of motion capture clips. We learn data-driven…
Dynamics Randomization Revisited:A Case Study for Quadrupedal Locomotion
Zhaoming Xie, Xingye Da, Michiel van de Panne +2
Understanding the gap between simulation and reality is critical for reinforcement learning with legged robots, which are largely trained in simulation. However, recent work has re…
Learning to Locomote: Understanding How Environment Design Matters for Deep Reinforcement Learning
Daniele Reda, Tianxin Tao, Michiel van de Panne
Learning to locomote is one of the most common tasks in physics-based animation and deep reinforcement learning (RL). A learned policy is the product of the problem to be solved, a…
ALLSTEPS: Curriculum-driven Learning of Stepping Stone Skills
Zhaoming Xie, Hung Yu Ling, Nam Hee Kim +1
Humans are highly adept at walking in environments with foot placement constraints, including stepping-stone scenarios where the footstep locations are fully constrained. Finding g…
Terrain RL Simulator
Glen Berseth, Xue Bin Peng, Michiel van de Panne
We provide challenging simulation environments that range in difficulty. The difficulty of solving a task is linked not only to the number of dimensions in the action space bu…
DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills
Xue Bin Peng, Pieter Abbeel, Sergey Levine +1
A longstanding goal in character animation is to combine data-driven specification of behavior with a system that can execute a similar behavior in a physical simulation, thus enab…
Feedback Control For Cassie With Deep Reinforcement Learning
Zhaoming Xie, Glen Berseth, Patrick Clary +2
Bipedal locomotion skills are challenging to develop. Control strategies often use local linearization of the dynamics in conjunction with reduced-order abstractions to yield tract…
Progressive Reinforcement Learning with Distillation for Multi-Skilled Motion Control
Glen Berseth, Cheng Xie, Paul Cernek +1
Deep reinforcement learning has demonstrated increasing capabilities for continuous control problems, including agents that can move with skill and agility through their environmen…