Search Results for author:
Found 27 papers, 13 papers with code
CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control
The former is capable of generating a wide variety of motions, adhering to intuitive control such as text, while the latter offers physically plausible motion and direct interaction with the environment.
Flexible Motion In-betweening with Diffusion Models
To this end, we propose Conditional Motion Diffusion In-betweening (CondMDI) which allows for arbitrary dense-or-sparse keyframe placement and partial keyframe constraints while generating high-quality motions that are diverse and coherent with the given keyframes.
Physics-based Motion Retargeting from Sparse Inputs
We introduce a method to retarget motions in real-time from sparse human sensor data to characters of various morphologies.
Understanding the Evolution of Linear Regions in Deep Reinforcement Learning
Empirically, we find that the region density increases only moderately throughout training, as measured along fixed trajectories coming from the final policy.
Learning Soccer Juggling Skills with Layer-wise Mixture-of-Experts
Learning physics-based character controllers that can successfully integrate diverse motor skills using a single policy remains a challenging problem.
Learning to Brachiate via Simplified Model Imitation
Key to our method is the use of a simplified model, a point mass with a virtual arm, for which we first learn a policy that can brachiate across handhold sequences with a prescribed order.
Learning to Get Up
Finally, a third stage learns control policies that can reproduce the weaker get-up motions at much slower speeds.
Evaluating Vision Transformer Methods for Deep Reinforcement Learning from Pixels
Vision Transformers (ViT) have recently demonstrated the significant potential of transformer architectures for computer vision.
A Survey on Reinforcement Learning Methods in Character Animation
Reinforcement Learning is an area of Machine Learning focused on how agents can be trained to make sequential decisions, and achieve a particular goal within an arbitrary environment.
Style-ERD: Responsive and Coherent Online Motion Style Transfer
Motion style transfer is a common method for enriching character animation.
Exploration with Multi-Sample Target Values for Distributional Reinforcement Learning
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 critic.
From Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligence
Machine learning has long since become a keystone technology, accelerating science and applications in a broad range of domains.
Discovering Diverse Athletic Jumping Strategies
We present a framework that enables the discovery of diverse and natural-looking motion strategies for athletic skills such as the high jump.
GLiDE: Generalizable Quadrupedal Locomotion in Diverse Environments with a Centroidal Model
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 robot.
Character Controllers Using Motion VAEs
A fundamental problem in computer animation is that of realizing purposeful and realistic human movement given a sufficiently-rich set of motion capture clips.
Learning to Locomote: Understanding How Environment Design Matters for Deep Reinforcement Learning
Learning to locomote is one of the most common tasks in physics-based animation and deep reinforcement learning (RL).
Learning Task-Agnostic Action Spaces for Movement Optimization
We propose a novel method for exploring the dynamics of physically based animated characters, and learning a task-agnostic action space that makes movement optimization easier.
ALLSTEPS: Curriculum-driven Learning of Stepping Stone Skills
Humans are highly adept at walking in environments with foot placement constraints, including stepping-stone scenarios where the footstep locations are fully constrained.
Learning to Correspond Dynamical Systems
Many dynamical systems exhibit similar structure, as often captured by hand-designed simplified models that can be used for analysis and control.
On Learning Symmetric Locomotion
We describe, compare, and evaluate four practical methods for encouraging motion symmetry.
Iterative Reinforcement Learning Based Design of Dynamic Locomotion Skills for Cassie
Deep reinforcement learning (DRL) is a promising approach for developing legged locomotion skills.
Robotics
DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills
We further explore a number of methods for integrating multiple clips into the learning process to develop multi-skilled agents capable of performing a rich repertoire of diverse skills.
Feedback Control For Cassie With Deep Reinforcement Learning
By formulating a feedback control problem as finding the optimal policy for a Markov Decision Process, we are able to learn robust walking controllers that imitate a reference motion with DRL.
Robotics
Progressive Reinforcement Learning with Distillation for Multi-Skilled Motion Control
Deep reinforcement learning has demonstrated increasing capabilities for continuous control problems, including agents that can move with skill and agility through their environment.
Model-Based Action Exploration for Learning Dynamic Motion Skills
Deep reinforcement learning has achieved great strides in solving challenging motion control tasks.
Learning Locomotion Skills Using DeepRL: Does the Choice of Action Space Matter?
The use of deep reinforcement learning allows for high-dimensional state descriptors, but little is known about how the choice of action representation impacts the learning difficulty and the resulting performance.
