Best Paper Award

Reinforcement Learning from Wild Animal Videos

Elliot Chane-Sane, Constant Roux, Olivier Stasse, Nicolas Mansard

Best Poster Award

Learning H-Infinity Locomotion Control

Junfeng Long, Wenye Yu, Quanyi Li, ZiRui Wang, Dahua Lin, Jiangmiao Pang

Accepted Papers

Learning a Risk-Averse Locomotion Policy from Uncertainty Estimates (M135)

Thomas B. Brunner, Takahiro Miki, Josip Josifovski, Joonho Lee, Alois Knoll, Marco Hutter

Dynamic Obstacle Avoidance with Bounded Rationality Adversarial Reinforcement Learning (M136)

Jose-Luis Holgado-Alvarez, Aryaman Reddi, Carlo D'Eramo

Learning Humanoid Locomotion with Perceptive Internal Model (M137)

Junfeng Long, Junli Ren, Moji Shi, ZiRui Wang, Tao Huang, Ping Luo, Jiangmiao Pang

Learning H-Infinity Locomotion Control (M138)
Junfeng Long, Wenye Yu, Quanyi Li, ZiRui Wang, Dahua Lin, Jiangmiao Pang

Motion Control of High-Dimensional Musculoskeletal System with Hierarchical Model-Based Planning (M139)

Yunyue Wei, Shanning Zhuang, Vincent Zhuang, Yanan Sui

Simple Masked Training Strategies Yield Control Policies That Are Robust to Sensor Failure (M140)
Skand Skand, Bikram Pandit, Chanho Kim, Fuxin Li, Stefan Lee

TLDR: Unsupervised Goal-Conditioned RL via Temporal Distance-Aware Representations (M141)

Junik Bae, Kwanyoung Park, Youngwoon Lee

Policy composition in reinforcement learning via multi-objective policy optimization (M142)
Shruti Mishra, Ankit Anand, Jordan Hoffmann, Nicolas Heess, Martin Riedmiller, Abbas Abdolmaleki, Doina Precup

Reinforcement Learning from Wild Animal Videos (A135)

Elliot Chane-Sane, Constant Roux, Olivier Stasse, Nicolas Mansard

AllGaits: Learning All Quadruped Gaits and Transitions (A136)

Guillaume Bellegarda, Milad Shafiee Ashtiani, Auke Ijspeert

Learning to Hop for a Single-legged Robot with Parallel Mechanism (A137)

Hongbo Zhang, Xiangyu Chu, Fei Yan Fiat Wong, Yun-Hui Liu, Kwok Wai Samuel Au

HAPmamba: Linear-Time Sequence Modeling for Terrain Classification by Legged Robots (A138)

Michał Wiliński, Krzysztof Walas, Mikołaj Łysakowski

RobotKeyframing: Learning Locomotion with High-Level Objectives via Mixture of Dense and Sparse Rewards (A139)

Fatemeh Zargarbashi, Jin Cheng, Dongho Kang, Robert Sumner, Stelian Coros

Latent Action Priors From a Single Gait Cycle Demonstration for Online Imitation Learning (A140)

Oliver Hausdörfer, Alexander von Rohr, Èric Lefort, Angela P. Schoellig

Parental Guidance: Efficient Lifelong Learning through Evolutionary Distillation (A141)

Rosario Scalise, Zhengyu Zhang