Results 281 to 290 of about 12,004,986 (327)
Some of the next articles are maybe not open access.

Any-point Trajectory Modeling for Policy Learning

Robotics: Science and Systems, 2023
Learning from demonstration is a powerful method for teaching robots new skills, and having more demonstration data often improves policy learning. However, the high cost of collecting demonstration data is a significant bottleneck.
Chuan Wen   +6 more
semanticscholar   +1 more source

Offline Model-Based Adaptable Policy Learning for Decision-Making in Out-of-Support Regions

IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023
In reinforcement learning, a promising direction to avoid online trial-and-error costs is learning from an offline dataset. Current offline reinforcement learning methods commonly learn in the policy space constrained to in-support regions by the offline
Xiong-Hui Chen   +6 more
semanticscholar   +1 more source

When policy learning meets policy styles

2021
We examine the classic four dimensions of policy style through a new perspective: policy learning. The approach of ‘modes of policy learning’ sheds light on the dynamic dimensions of anticipation, reaction, consensus and imposition that characterise policy styles in terms of problem solving and relationships among actors. What is the learning mode that
Dunlop, CA, Radaelli, CM
openaire   +3 more sources

Policy Learning and Policy Failure

2020
First published as a special issue of Policy & Politics, this updated volume explores policy failures and the valuable opportunities for learning that they offer. The book begins with an overview of policy learning and policy failure. The links between the two appear obvious, yet there are very few studies that address how one can learn from ...
  +6 more sources

Pessimistic Reward Models for Off-Policy Learning in Recommendation

ACM Conference on Recommender Systems, 2021
Methods for bandit learning from user interactions often require a model of the reward a certain context-action pair will yield – for example, the probability of a click on a recommendation. This common machine learning task is highly non-trivial, as the
Olivier Jeunen, Bart Goethals
semanticscholar   +1 more source

Dreamitate: Real-World Visuomotor Policy Learning via Video Generation

Conference on Robot Learning
A key challenge in manipulation is learning a policy that can robustly generalize to diverse visual environments. A promising mechanism for learning robust policies is to leverage video generative models, which are pretrained on large-scale datasets of ...
Junbang Liang   +7 more
semanticscholar   +1 more source

Automated Creation of Digital Cousins for Robust Policy Learning

Conference on Robot Learning
Training robot policies in the real world can be unsafe, costly, and difficult to scale. Simulation serves as an inexpensive and potentially limitless source of training data, but suffers from the semantics and physics disparity between simulated and ...
Tianyuan Dai   +7 more
semanticscholar   +1 more source

Policy learning governance: a new perspective on agency across policy learning theories

Policy & Politics
The predominant ontological position on agency in policy learning literature has been relatively learner-oriented, thus focusing on policy actors puzzling about policy problems. In other words, it focuses on how actors acquire, translate, and disseminate
B. Zaki
semanticscholar   +1 more source

Policy Learning

Published online: 26 February 2025 Policy learning is the discursive interactive practice whereby political actors update their cognitive orientations and normative beliefs (and change policy accordingly), resulting from knowledge and information feedback.
HEMERIJCK, Anton, BOKHORST, David Jonas
openaire   +2 more sources

POLICY LEARNING

Australian Journal of Public Administration, 1994
The Comparative History of Public Policy. Edited by Francis G. Castles Trends in British Public Policy: Do Governments Make any Difference? Brian W. Hogwood Public Policy in Britain.
openaire   +1 more source

Home - About - Disclaimer - Privacy