Results 241 to 250 of about 8,179,762 (306)

Disturbance-Observer-Based Tracking Controller for Neural Network Driving Policy Transfer

IEEE transactions on intelligent transportation systems (Print), 2020
The neural network policies are widely explored in the autonomous driving field, thanks to their capability of handling complicated driving tasks. However, the practical deployment of such policies is slowed down due to their lack of robustness against ...
Chen Tang, Zhuo Xu, M. Tomizuka
semanticscholar   +1 more source

TRANSIC: Sim-to-Real Policy Transfer by Learning from Online Correction

Conference on Robot Learning
Learning in simulation and transferring the learned policy to the real world has the potential to enable generalist robots. The key challenge of this approach is to address simulation-to-reality (sim-to-real) gaps.
Yunfan Jiang, Chen Wang, Ruohan Zhang, Jiajun Wu, Fei-Fei Li   +4 more
semanticscholar   +1 more source

Mirage: Cross-Embodiment Zero-Shot Policy Transfer with Cross-Painting

Robotics: Science and Systems Conference
The ability to reuse collected data and transfer trained policies between robots could alleviate the burden of additional data collection and training.
L. Chen, Kush Hari, K. Dharmarajan, Chenfeng Xu, Quan Vuong, Kenneth Y. Goldberg   +5 more
semanticscholar   +1 more source

Using Bisimulation for Policy Transfer in MDPs

Proceedings of the AAAI Conference on Artificial Intelligence, 2010
Knowledge transfer has been suggested as a useful approach for solving large Markov Decision Processes. The main idea is to compute a decision-making policy in one environment and use it in a different environment, provided the two are ”close enough”.
Pablo Samuel Castro, Doina Precup
openaire   +2 more sources

A Comprehensive Survey of Cross-Domain Policy Transfer for Embodied Agents

International Joint Conference on Artificial Intelligence
The burgeoning fields of robot learning and embodied AI have triggered an increasing demand for large quantities of data. However, collecting sufficient unbiased data from the target domain remains a challenge due to costly data collection processes and ...
Haoyi Niu, Jianming Hu, Guyue Zhou, Xianyuan Zhan   +3 more
semanticscholar   +1 more source

Efficient Deep Reinforcement Learning through Policy Transfer

Adaptive Agents and Multi-Agent Systems, 2020
Transfer Learning (TL) has shown great potential to accelerate Reinforcement Learning (RL) by leveraging prior knowledge from past learned policies of relevant tasks.
Tianpei Yang, Jianye Hao, Zhaopeng Meng, Zongzhang Zhang, Weixun Wang, Yujing Hu, Yingfeng Chen, Changjie Fan, Zhaodong Wang, J. Peng   +9 more
semanticscholar   +1 more source

Policy Transfer and Everyday Policy-Making

2015
We have established two key propositions thus far. First, that the SCPO is a novel measure for serious and organised crime control, in that no such civil-criminal hybrid statutory instrument has been previously used to regulate or control the behaviour of individuals engaging in serious or organised criminal behaviour.
openaire   +2 more sources

Policy transfer in Asia

2021
Owing to the institutional diversity within the region, policy transfer among countries in Asia is often not used to explain domestic policy changes. But the growing evidence of the spread of policies in various areas within the region suggests otherwise.
Saguin, K., Sha, K.
openaire   +2 more sources

Policy transfer: the case of European Union–China cooperation in public administration reform

International Review of Administrative Sciences, 2019
This article addresses the Chinese government’s accelerated process of administrative reform and focuses on the decade-long effort by China to develop transfer policies with selected European nations. Providing more efficient public services and building
Yanzhe Zhang, Xiao Yu
semanticscholar   +1 more source

Policy Transfer and the Internationalisation of Social Policy

Social Policy and Society, 2005
This article analyses the theoretical utility of policy transfer in developing perspectives on international and comparative social policy. It argues that existing work on policy transfer provides us with a theoretical tool to connect perspectives on international policy change, by focussing on the knowledge base of policy and the motivations of actors
openaire   +1 more source