Policy learning and change during crisis: COVID-19 policy responses across six states. [PDF]
Rev Policy Res, 2023 Whereas policy change is often characterized as a gradual and incremental process, effective crisis response necessitates that organizations adapt to evolving problems in near real time.
Crow DA +9 more
europepmc +2 more sources
BATCH POLICY LEARNING IN AVERAGE REWARD MARKOV DECISION PROCESSES. [PDF]
Ann Stat, 2022 We consider the batch (off-line) policy learning problem in the infinite horizon Markov Decision Process. Motivated by mobile health applications, we focus on learning a policy that maximizes the long-term average reward.
Liao P +4 more
europepmc +3 more sources
Policy learning and crisis policy-making: quadruple-loop learning and COVID-19 responses in South Korea. [PDF]
Policy Soc, 2020 This study aims to analyze how the Korean government has been effective in taming COVID-19 without forced interruptions (i.e. lockdowns) of citizens’ daily lives.
Lee S, Hwang C, Moon MJ.
europepmc +2 more sources
Policy learning and policy failure:
Policy & Politics, 2017 Policy failures present a valuable opportunity for policy learning, but public officials often fail to learn valuable lessons from these experiences. The studies in this volume investigate this broken link. This introduction defines policy learning and failure, and then organises the main studies in these fields along the key dimensions of: processes ...
C. Dunlop
openaire +4 more sources
Diffusion policy: Visuomotor policy learning via action diffusion [PDF]
Robotics: Science and Systems, 2023 This paper introduces Diffusion Policy, a new way of generating robot behavior by representing a robot’s visuomotor policy as a conditional denoising diffusion process.
Cheng Chi +6 more
semanticscholar +1 more source
Accelerated Policy Learning with Parallel Differentiable Simulation [PDF]
International Conference on Learning Representations, 2022 Deep reinforcement learning can generate complex control policies, but requires large amounts of training data to work effectively. Recent work has attempted to address this issue by leveraging differentiable simulators.
Jie Xu +6 more
semanticscholar +1 more source
UniDexGrasp++: Improving Dexterous Grasping Policy Learning via Geometry-aware Curriculum and Iterative Generalist-Specialist Learning [PDF]
IEEE International Conference on Computer Vision, 2023 We propose a novel, object-agnostic method for learning a universal policy for dexterous object grasping from realistic point cloud observations and proprioceptive information under a table-top setting, namely UniDexGrasp++.
Haoran Geng, Yun Liu
semanticscholar +1 more source
ChessGPT: Bridging Policy Learning and Language Modeling [PDF]
Neural Information Processing Systems, 2023 When solving decision-making tasks, humans typically depend on information from two key sources: (1) Historical policy data, which provides interaction replay from the environment, and (2) Analytical insights in natural language form, exposing the ...
Xidong Feng +8 more
semanticscholar +1 more source
Unified Conversational Recommendation Policy Learning via Graph-based Reinforcement Learning [PDF]
Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 2021 Conversational recommender systems (CRS) enable the traditional recommender systems to explicitly acquire user preferences towards items and attributes through interactive conversations.
Yang Deng +4 more
semanticscholar +1 more source
Adaptive Policy Learning for Offline-to-Online Reinforcement Learning [PDF]
AAAI Conference on Artificial Intelligence, 2023 Conventional reinforcement learning (RL) needs an environment to collect fresh data, which is impractical when online interactions are costly. Offline RL provides an alternative solution by directly learning from the previously collected dataset. However,
Han Zheng +5 more
semanticscholar +1 more source