English
Related papers

Related papers: SkillMimic-V2: Learning Robust and Generalizable I…

200 papers

Applying reinforcement learning (RL) to sparse reward domains is notoriously challenging due to insufficient guiding signals. Common RL techniques for addressing such domains include (1) learning from demonstrations and (2) curriculum…

Machine Learning · Computer Science 2023-03-29 Vaibhav Bajaj , Guni Sharon , Peter Stone

Reinforcement learning (RL) faces substantial challenges when applied to real-life problems, primarily stemming from the scarcity of available data due to limited interactions with the environment. This limitation is exacerbated by the fact…

Neural and Evolutionary Computing · Computer Science 2024-04-10 Cristiano Capone , Paolo Muratore

Spatiotemporal Traffic Data (STTD) measures the complex dynamical behaviors of the multiscale transportation system. Existing methods aim to reconstruct STTD using low-dimensional models. However, they are limited to data-specific…

Machine Learning · Computer Science 2024-10-25 Tong Nie , Guoyang Qin , Wei Ma , Jian Sun

In the context of safe exploration, Reinforcement Learning (RL) has long grappled with the challenges of balancing the tradeoff between maximizing rewards and minimizing safety violations, particularly in complex environments with…

Machine Learning · Computer Science 2023-12-13 Simon Sinong Zhan , Yixuan Wang , Qingyuan Wu , Ruochen Jiao , Chao Huang , Qi Zhu

Trainable activation functions, whose parameters are optimized alongside network weights, offer increased expressivity compared to fixed activation functions. Specifically, trainable activation functions defined as ratios of polynomials…

Machine Learning · Computer Science 2025-07-22 Rafał Surdej , Michał Bortkiewicz , Alex Lewandowski , Mateusz Ostaszewski , Clare Lyle

In sim-to-real Reinforcement Learning (RL), a policy is trained in a simulated environment and then deployed on the physical system. The main challenge of sim-to-real RL is to overcome the reality gap - the discrepancies between the real…

Robotics · Computer Science 2023-06-13 Nghia Vuong , Quang-Cuong Pham

Training deep reinforcement learning (DRL) models usually requires high computation costs. Therefore, compressing DRL models possesses immense potential for training acceleration and model deployment. However, existing methods that generate…

Machine Learning · Computer Science 2023-03-09 Yiqin Tan , Pihe Hu , Ling Pan , Jiatai Huang , Longbo Huang

This work presents reinforcement learning (RL)-driven data augmentation to improve the generalization of vision-action (VA) models for dexterous grasping. While real-to-sim-to-real frameworks, where a few real demonstrations seed…

Robotics · Computer Science 2025-04-28 Atsushi Kanehira , Naoki Wake , Kazuhiro Sasabuchi , Jun Takamatsu , Katsushi Ikeuchi

Sensors are commonly deployed to perceive the environment. However, due to the high cost, sensors are usually sparsely deployed. Kriging is the tailored task to infer the unobserved nodes (without sensors) using the observed source nodes…

Machine Learning · Computer Science 2025-01-13 Qianxiong Xu , Cheng Long , Ziyue Li , Sijie Ruan , Rui Zhao , Zhishuai Li

Deep reinforcement learning (RL) has shown immense potential for learning to control systems through data alone. However, one challenge deep RL faces is that the full state of the system is often not observable. When this is the case, the…

Machine Learning · Computer Science 2023-10-27 Ian Char , Jeff Schneider

Model-free control strategies such as reinforcement learning have shown the ability to learn control strategies without requiring an accurate model or simulator of the world. While this is appealing due to the lack of modeling requirements,…

Robotics · Computer Science 2024-06-28 Marius Memmel , Andrew Wagenmaker , Chuning Zhu , Patrick Yin , Dieter Fox , Abhishek Gupta

Representation learning and unsupervised skill discovery can allow robots to acquire diverse and reusable behaviors without the need for task-specific rewards. In this work, we use unsupervised reinforcement learning to learn a latent…

Contact-rich manipulation involves kinematic constraints on the task motion, typically with discrete transitions between these constraints during the task. Allowing the robot to detect and reason about these contact constraints can support…

Robotics · Computer Science 2023-04-05 Christian Hegeler , Filippo Rozzi , Loris Roveda , Kevin Haninger

Sequential processes in real-world often carry a combination of simple subsystems that interact with each other in certain forms. Learning such a modular structure can often improve the robustness against environmental changes. In this…

Machine Learning · Computer Science 2023-11-07 Ziyu Wang , Wenhao Jiang , Zixuan Zhang , Wei Tang , Junchi Yan

Humanoid whole-body loco-manipulation promises transformative capabilities for daily service and warehouse tasks. While recent advances in general motion tracking (GMT) have enabled humanoids to reproduce diverse human motions, these…

Robotics · Computer Science 2025-10-09 Siheng Zhao , Yanjie Ze , Yue Wang , C. Karen Liu , Pieter Abbeel , Guanya Shi , Rocky Duan

Recent advances in reinforcement learning (RL) have strengthened the reasoning capabilities of vision-language models (VLMs). However, enhancing policy exploration to better scale test-time compute remains largely underexplored. In…

Computer Vision and Pattern Recognition · Computer Science 2025-11-03 Xiangyan Liu , Jinjie Ni , Zijian Wu , Chao Du , Longxu Dou , Haonan Wang , Tianyu Pang , Michael Qizhe Shieh

To integrate into human-centered environments, autonomous agents must learn from and adapt to humans in their native settings. Preference-based reinforcement learning (PbRL) can enable this by learning reward functions from human…

Reinforcement Learning (RL) has become essential for eliciting complex reasoning capabilities in Large Language Models (LLMs). However, the substantial memory overhead of storing Key-Value (KV) caches during long-horizon rollouts acts as a…

Machine Learning · Computer Science 2026-03-31 Sijia Luo , Xiaokang Zhang , Yuxuan Hu , Bohan Zhang , Ke Wang , Jinbo Su , Mengshu Sun , Lei Liang , Jing Zhang

Existing person re-identification (re-id) methods mostly rely on supervised model learning from a large set of person identity labelled training data per domain. This limits their scalability and usability in large scale deployments. In…

Computer Vision and Pattern Recognition · Computer Science 2021-01-19 Minxian Li , Xiatian Zhu , Shaogang Gong

Sim-to-Real refers to the process of transferring policies learned in simulation to the real world, which is crucial for achieving practical robotics applications. However, recent Sim2real methods either rely on a large amount of augmented…

Robotics · Computer Science 2025-02-25 Yuxuan Wu , Lei Pan , Wenhua Wu , Guangming Wang , Yanzi Miao , Fan Xu , Hesheng Wang