Specifying reward signals that allow agents to learn complex behaviors i...
In this work, we present Conditional Adversarial Latent Models (CALM), a...
This work aims to push the limits of agility for bipedal robots by enabl...
Movement is how people interact with and affect their environment. For
r...
Developing systems that can synthesize natural and life-like motions for...
We present a reinforcement learning (RL) framework that enables quadrupe...
Recent years have seen a surge in commercially-available and affordable
...
We address the problem of enabling quadrupedal robots to perform precise...
The incredible feats of athleticism demonstrated by humans are made poss...
Training a high-dimensional simulated agent with an under-specified rewa...
We introduce Contrastive Intrinsic Control (CIC), an algorithm for
unsup...
Legged robots are physically capable of traversing a wide range of
chall...
Synthesizing graceful and life-like behaviors for physically simulated
c...
Developing robust walking controllers for bipedal robots is a challengin...
Massive datasets have proven critical to successfully applying deep lear...
Reproducing the diverse and agile locomotion skills of animals has been ...
Reinforcement learning offers the promise of automating the acquisition ...
In this paper, we aim to develop a simple and scalable reinforcement lea...
Reinforcement learning agents that operate in diverse and complex
enviro...
Humans are able to perform a myriad of sophisticated tasks by drawing up...
Data-driven character animation based on motion capture can produce high...
Adversarial learning methods have been proposed for a wide range of
appl...
We provide 89 challenging simulation environments that range in difficul...
A longstanding goal in character animation is to combine data-driven
spe...
Simulations are attractive environments for training agents as they prov...
The use of deep reinforcement learning allows for high-dimensional state...