Avatars are important to create interactive and immersive experiences in...
Humans perform everyday tasks using a combination of locomotion and
mani...
Policies produced by deep reinforcement learning are typically character...
Reinforcement Learning (RL) has seen many recent successes for quadruped...
Brachiation is the primary form of locomotion for gibbons and siamangs, ...
Vision Transformers (ViT) have recently demonstrated the significant
pot...
Reinforcement Learning is an area of Machine Learning focused on how age...
Motion style transfer is a common method for enriching character animati...
Distributional reinforcement learning (RL) aims to learn a value-network...
Machine learning has long since become a keystone technology, accelerati...
We present a framework that enables the discovery of diverse and
natural...
Model-free reinforcement learning (RL) for legged locomotion commonly re...
A fundamental problem in computer animation is that of realizing purpose...
Understanding the gap between simulation andreality is critical for
rein...
Learning to locomote is one of the most common tasks in physics-based
an...
We propose a novel method for exploring the dynamics of physically based...
Humans are highly adept at walking in environments with foot placement
c...
Correspondence across dynamical systems can lend us better tools for lea...
Deep reinforcement learning (DRL) is a promising approach for developing...
We provide 89 challenging simulation environments that range in difficul...
A longstanding goal in character animation is to combine data-driven
spe...
Bipedal locomotion skills are challenging to develop. Control strategies...
Deep reinforcement learning has demonstrated increasing capabilities for...
Deep reinforcement learning has great stride in solving challenging moti...
The use of deep reinforcement learning allows for high-dimensional state...