English
Related papers

Related papers: Unsupervised Skill Discovery as Exploration for Le…

200 papers

Unsupervised Skill Discovery (USD) allows agents to autonomously learn diverse behaviors without task-specific rewards. While recent USD methods have shown promise, their application to real-world robotics remains underexplored. In this…

Robotics · Computer Science 2025-09-01 Rafael Cathomen , Mayank Mittal , Marin Vlastelica , Marco Hutter

Unsupervised Reinforcement Learning (RL) aims to discover diverse behaviors that can accelerate the learning of downstream tasks. Previous methods typically focus on entropy-based exploration or empowerment-driven skill learning. However,…

Machine Learning · Computer Science 2025-06-18 Ting Xiao , Jiakun Zheng , Rushuai Yang , Kang Xu , Qiaosheng Zhang , Peng Liu , Chenjia Bai

Designing control policies for legged locomotion is complex due to the under-actuated and non-continuous robot dynamics. Model-free reinforcement learning provides promising tools to tackle this challenge. However, a major bottleneck of…

Robotics · Computer Science 2022-03-08 Tsung-Yen Yang , Tingnan Zhang , Linda Luu , Sehoon Ha , Jie Tan , Wenhao Yu

Model free reinforcement learning suffers from the high sampling complexity inherent to robotic manipulation or locomotion tasks. Most successful approaches typically use random sampling strategies which leads to slow policy convergence. In…

Robotics · Computer Science 2019-08-13 Miroslav Bogdanovic , Ludovic Righetti

Recent advances in quadrupedal robots have demonstrated impressive agility and the ability to traverse diverse terrains. However, hardware issues, such as motor overheating or joint locking, may occur during long-distance walking or…

Robotics · Computer Science 2025-02-11 Seunghyun Lee , I Made Aswin Nahrendra , Dongkyu Lee , Byeongho Yu , Minho Oh , Hyun Myung

Robots can rapidly acquire new skills from demonstrations. However, during generalisation of skills or transitioning across fundamentally different skills, it is unclear whether the robot has the necessary knowledge to perform the task.…

Machine Learning · Statistics 2018-08-08 Nutan Chen , Alexej Klushyn , Alexandros Paraschos , Djalel Benbouzid , Patrick van der Smagt

We propose Scheduled Auxiliary Control (SAC-X), a new learning paradigm in the context of Reinforcement Learning (RL). SAC-X enables learning of complex behaviors - from scratch - in the presence of multiple sparse reward signals. To this…

Although Deep Reinforcement Learning (DRL) has been popular in many disciplines including robotics, state-of-the-art DRL algorithms still struggle to learn long-horizon, multi-step and sparse reward tasks, such as stacking several blocks…

Robotics · Computer Science 2023-03-10 Xintong Yang , Ze Ji , Jing Wu , Yu-kun Lai

Knowledge from animals and humans inspires robotic innovations. Numerous efforts have been made to achieve agile locomotion in quadrupedal robots through classical controllers or reinforcement learning approaches. These methods usually rely…

Quadrupedal robots have demonstrated exceptional locomotion capabilities through Reinforcement Learning (RL), including extreme parkour maneuvers. However, integrating locomotion skills with navigation in quadrupedal robots has not been…

Robotics · Computer Science 2025-09-09 Dewei Wang , Chenjia Bai , Chenhui Li , Jiyuan Shi , Yan Ding , Chi Zhang , Bin Zhao

We tackle the problem of perceptive locomotion in dynamic environments. In this problem, a quadrupedal robot must exhibit robust and agile walking behaviors in response to environmental clutter and moving obstacles. We present a…

Robotics · Computer Science 2023-02-21 Mingyo Seo , Ryan Gupta , Yifeng Zhu , Alexy Skoutnev , Luis Sentis , Yuke Zhu

Learning to locomote to arbitrary goals on hardware remains a challenging problem for reinforcement learning. In this paper, we present a hierarchical learning framework that improves sample-efficiency and generalizability of locomotion…

Robotics · Computer Science 2019-09-30 Tianyu Li , Nathan Lambert , Roberto Calandra , Franziska Meier , Akshara Rai

Modern Reinforcement Learning (RL) algorithms promise to solve difficult motor control problems directly from raw sensory inputs. Their attraction is due in part to the fact that they can represent a general class of methods that allow to…

Reinforcement learning algorithms commonly seek to optimize policies for solving one particular task. How should we explore an unknown dynamical system such that the estimated model globally approximates the dynamics and allows us to solve…

Machine Learning · Computer Science 2023-10-31 Bhavya Sukhija , Lenart Treven , Cansu Sancaktar , Sebastian Blaes , Stelian Coros , Andreas Krause

Quadrupedal robots resemble the physical ability of legged animals to walk through unstructured terrains. However, designing a controller for quadrupedal robots poses a significant challenge due to their functional complexity and requires…

Robotics · Computer Science 2023-03-06 I Made Aswin Nahrendra , Byeongho Yu , Hyun Myung

Locomotion has seen dramatic progress for walking or running across challenging terrains. However, robotic quadrupeds are still far behind their biological counterparts, such as dogs, which display a variety of agile skills and can use the…

Robotics · Computer Science 2023-03-23 Xuxin Cheng , Ashish Kumar , Deepak Pathak

Bimanual dexterous manipulation is a critical yet underexplored area in robotics. Its high-dimensional action space and inherent task complexity present significant challenges for policy learning, and the limited task diversity in existing…

Robotics · Computer Science 2024-10-04 Bohan Zhou , Haoqi Yuan , Yuhui Fu , Zongqing Lu

Exploration efficiency poses a significant challenge in goal-conditioned reinforcement learning (GCRL) tasks, particularly those with long horizons and sparse rewards. A primary limitation to exploration efficiency is the agent's inability…

Machine Learning · Computer Science 2024-04-22 Lisheng Wu , Ke Chen

Agile and adaptive maneuvers such as fall recovery, high-speed turning, and sprinting in the wild are challenging for legged systems. We propose a Curricular Hindsight Reinforcement Learning (CHRL) that learns an end-to-end tracking…

Robotics · Computer Science 2023-10-25 Sicen Li , Yiming Pang , Panju Bai , Zhaojin Liu , Jiawei Li , Shihao Hu , Liquan Wang , Gang Wang

This paper investigates the automatic exploration problem under the unknown environment, which is the key point of applying the robotic system to some social tasks. The solution to this problem via stacking decision rules is impossible to…

Robotics · Computer Science 2020-07-24 Haoran Li , Qichao Zhang , Dongbin Zhao