中文
相关论文

相关论文: GACL: Grounded Adaptive Curriculum Learning with A…

200 篇论文

The high cost of real-world data for robotics Reinforcement Learning (RL) leads to the wide usage of simulators. Despite extensive work on building better dynamics models for simulators to match with the real world, there is another,…

机器人学 · 计算机科学 2024-10-01 Linji Wang , Zifan Xu , Peter Stone , Xuesu Xiao

Curriculum learning has demonstrated substantial effectiveness in robot learning. However, it still faces limitations when scaling to complex, wide-ranging task spaces. Such task spaces often lack a well-defined difficulty structure, making…

机器人学 · 计算机科学 2026-01-27 Ziming Li , Chenhao Li , Marco Hutter

This study is aimed at addressing the problem of fault tolerance of quadruped robots to actuator failure, which is critical for robots operating in remote or extreme environments. In particular, an adaptive curriculum reinforcement learning…

机器人学 · 计算机科学 2024-10-28 Wataru Okamoto , Hiroshi Kera , Kazuhiko Kawamoto

Automatic Curriculum Learning (ACL) has become a cornerstone of recent successes in Deep Reinforcement Learning (DRL).These methods shape the learning trajectories of agents by challenging them with tasks adapted to their capacities. In…

机器学习 · 计算机科学 2020-06-01 Rémy Portelas , Cédric Colas , Lilian Weng , Katja Hofmann , Pierre-Yves Oudeyer

Despite advances in Reinforcement Learning, many sequential decision making tasks remain prohibitively expensive and impractical to learn. Recently, approaches that automatically generate reward functions from logical task specifications…

人工智能 · 计算机科学 2023-04-12 Yash Shukla , Abhishek Kulkarni , Robert Wright , Alvaro Velasquez , Jivko Sinapov

Various automatic curriculum learning (ACL) methods have been proposed to improve the sample efficiency and final performance of deep reinforcement learning (DRL). They are designed to control how a DRL agent collects data, which is…

机器学习 · 计算机科学 2022-10-26 Jikun Kang , Miao Liu , Abhinav Gupta , Chris Pal , Xue Liu , Jie Fu

The domain of robotics is challenging to apply deep reinforcement learning due to the need for large amounts of data and for ensuring safety during learning. Curriculum learning has shown good performance in terms of sample- efficient deep…

机器人学 · 计算机科学 2022-04-15 Anil Kurkcu , Cihan Acar , Domenico Campolo , Keng Peng Tee

A major challenge in the Deep RL (DRL) community is to train agents able to generalize their control policy over situations never seen in training. Training on diverse tasks has been identified as a key ingredient for good generalization,…

机器学习 · 计算机科学 2021-09-02 Rémy Portelas , Clément Romac , Katja Hofmann , Pierre-Yves Oudeyer

We present NavACL, a method of automatic curriculum learning tailored to the navigation task. NavACL is simple to train and efficiently selects relevant tasks using geometric features. In our experiments, deep reinforcement learning agents…

机器人学 · 计算机科学 2021-01-07 Steven D. Morad , Roberto Mecca , Rudra P. K. Poudel , Stephan Liwicki , Roberto Cipolla

Reinforcement learning has shown great promise in the training of robot behavior due to the sequential decision making characteristics. However, the required enormous amount of interactive and informative training data provides the major…

人工智能 · 计算机科学 2020-12-22 Sha Luo , Hamidreza Kasaei , Lambert Schomaker

Goal-conditioned reinforcement learning has shown considerable potential in robotic manipulation; however, existing approaches remain limited by their reliance on prioritizing collected experience, resulting in suboptimal performance across…

机器人学 · 计算机科学 2026-04-15 Xuerui Wang , Guangyu Ren , Tianhong Dai , Bintao Hu , Shuangyao Huang , Wenzhang Zhang , Hengyan Liu

Human beings can quickly adapt to environmental changes by leveraging learning experience. However, adapting deep neural networks to dynamic environments by machine learning algorithms remains a challenge. To better understand this issue,…

计算机视觉与模式识别 · 计算机科学 2021-03-24 Shixiang Tang , Peng Su , Dapeng Chen , Wanli Ouyang

Gradient-based meta-learners such as Model-Agnostic Meta-Learning (MAML) have shown strong few-shot performance in supervised and reinforcement learning settings. However, specifically in the case of meta-reinforcement learning (meta-RL),…

机器学习 · 计算机科学 2020-02-20 Bhairav Mehta , Tristan Deleu , Sharath Chandra Raparthy , Chris J. Pal , Liam Paull

This paper explores the integration of incremental curriculum learning (ICL) with deep reinforcement learning (DRL) techniques to facilitate mobile robot navigation through task-based human instruction. By adopting a curriculum that mirrors…

机器人学 · 计算机科学 2024-12-30 Muhammad A. Muttaqien , Ayanori Yorozu , Akihisa Ohya

Deep reinforcement learning (DRL) has been widely applied in autonomous exploration and mapping tasks, but often struggles with the challenges of sampling efficiency, poor adaptability to unknown map sizes, and slow simulation speed. To…

机器人学 · 计算机科学 2023-02-28 Zhi Li , Jinghao Xin , Ning Li

Recent advances in multi-agent reinforcement learning (MARL) allow agents to coordinate their behaviors in complex environments. However, common MARL algorithms still suffer from scalability and sparse reward issues. One promising approach…

人工智能 · 计算机科学 2023-02-08 Rundong Wang , Longtao Zheng , Wei Qiu , Bowei He , Bo An , Zinovi Rabinovich , Yujing Hu , Yingfeng Chen , Tangjie Lv , Changjie Fan

This paper addresses the challenges of training end-to-end autonomous driving agents using Reinforcement Learning (RL). RL agents are typically trained in a fixed set of scenarios and nominal behavior of surrounding road users in…

机器人学 · 计算机科学 2026-03-06 Ahmed Abouelazm , Tim Weinstein , Tim Joseph , Philip Schörner , J. Marius Zöllner

Reinforcement Learning is a mature technology, often suggested as a potential route towards Artificial General Intelligence, with the ambitious goal of replicating the wide range of abilities found in natural and artificial intelligence,…

机器学习 · 计算机科学 2025-11-25 Markus D. Solbach , John K. Tsotsos

The Reinforcement Learning (RL) paradigm has been an essential tool for automating robotic tasks. Despite the advances in RL, it is still not widely adopted in the industry due to the need for an expensive large amount of robot interaction…

机器人学 · 计算机科学 2022-04-29 Cristian C. Beltran-Hernandez , Damien Petit , Ixchel G. Ramirez-Alpizar , Kensuke Harada

This paper investigates the impact of using gradient norm reward signals in the context of Automatic Curriculum Learning (ACL) for deep reinforcement learning (DRL). We introduce a framework where the teacher model, utilizing the gradient…

机器学习 · 计算机科学 2023-12-22 Ryan Campbell , Junsang Yoon
‹ 上一页 1 2 3 10 下一页 ›