Search Results for author: Michiel Van de Panne

Found 22 papers, 10 papers with code

Learning to Brachiate via Simplified Model Imitation

1 code implementation8 May 2022 Daniele Reda, Hung Yu Ling, Michiel Van de Panne

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.

14 reinforcement-learning

Learning to Get Up

1 code implementation30 Apr 2022 Tianxin Tao, Matthew Wilson, Ruiyu Gou, Michiel Van de Panne

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

no code implementations11 Apr 2022 Tianxin Tao, Daniele Reda, Michiel Van de Panne

Vision Transformers (ViT) have recently demonstrated the significant potential of transformer architectures for computer vision.

Contrastive Learning reinforcement-learning

A Survey on Reinforcement Learning Methods in Character Animation

no code implementations7 Mar 2022 Ariel Kwiatkowski, Eduardo Alvarado, Vicky Kalogeiton, C. Karen Liu, Julien Pettré, Michiel Van de Panne, Marie-Paule Cani

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.

reinforcement-learning

Exploration with Multi-Sample Target Values for Distributional Reinforcement Learning

no code implementations6 Feb 2022 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 critic.

Continuous Control Distributional Reinforcement Learning +1

Discovering Diverse Athletic Jumping Strategies

no code implementations2 May 2021 Zhiqi Yin, Zeshi Yang, Michiel Van de Panne, KangKang Yin

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

no code implementations20 Apr 2021 Zhaoming Xie, Xingye Da, Buck Babich, Animesh Garg, Michiel Van de Panne

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

1 code implementation26 Mar 2021 Hung Yu Ling, Fabio Zinno, George Cheng, Michiel Van de Panne

A fundamental problem in computer animation is that of realizing purposeful and realistic human movement given a sufficiently-rich set of motion capture clips.

Continuous Control motion synthesis +1

Learning to Locomote: Understanding How Environment Design Matters for Deep Reinforcement Learning

no code implementations9 Oct 2020 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).

reinforcement-learning

Learning Task-Agnostic Action Spaces for Movement Optimization

1 code implementation22 Sep 2020 Amin Babadi, Michiel Van de Panne, C. Karen Liu, Perttu Hämäläinen

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

1 code implementation9 May 2020 Zhaoming Xie, Hung Yu Ling, Nam Hee Kim, Michiel Van de Panne

Humans are highly adept at walking in environments with foot placement constraints, including stepping-stone scenarios where the footstep locations are fully constrained.

reinforcement-learning

Learning to Correspond Dynamical Systems

no code implementations L4DC 2020 Nam Hee Kim, Zhaoming Xie, Michiel Van de Panne

Many dynamical systems exhibit similar structure, as often captured by hand-designed simplified models that can be used for analysis and control.

Iterative Reinforcement Learning Based Design of Dynamic Locomotion Skills for Cassie

1 code implementation22 Mar 2019 Zhaoming Xie, Patrick Clary, Jeremy Dao, Pedro Morais, Jonathan Hurst, Michiel Van de Panne

Deep reinforcement learning (DRL) is a promising approach for developing legged locomotion skills.

Robotics

Terrain RL Simulator

1 code implementation17 Apr 2018 Glen Berseth, Xue Bin Peng, Michiel Van de Panne

We provide $89$ challenging simulation environments that range in difficulty.

DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills

6 code implementations8 Apr 2018 Xue Bin Peng, Pieter Abbeel, Sergey Levine, Michiel Van de Panne

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.

reinforcement-learning

Feedback Control For Cassie With Deep Reinforcement Learning

3 code implementations15 Mar 2018 Zhaoming Xie, Glen Berseth, Patrick Clary, Jonathan Hurst, Michiel Van de Panne

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

no code implementations ICLR 2018 Glen Berseth, Cheng Xie, Paul Cernek, Michiel Van de Panne

Deep reinforcement learning has demonstrated increasing capabilities for continuous control problems, including agents that can move with skill and agility through their environment.

Continuous Control reinforcement-learning +1

Model-Based Action Exploration for Learning Dynamic Motion Skills

no code implementations11 Jan 2018 Glen Berseth, Michiel Van de Panne

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?

no code implementations3 Nov 2016 Xue Bin Peng, Michiel Van de Panne

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.

reinforcement-learning

Cannot find the paper you are looking for? You can Submit a new open access paper.