Results 1 to 10 of about 25,414,586 (332)
Built Environment Design and People with Autism Spectrum Disorder (ASD): A Scoping Review. [PDF]
Int J Environ Res Public Health, 2021 Built environment design can be considered as an influential factor in the quality of life of people with autism spectrum disorder (ASD). This scoping review provides an overview of the current available literature on the relationship between people with
Tola G +4 more
europepmc +2 more sources
Evolving Curricula with Regret-Based Environment Design [PDF]
International Conference on Machine Learning, 2022 It remains a significant challenge to train generally capable agents with reinforcement learning (RL). A promising avenue for improving the robustness of RL agents is through the use of curricula.
Jack Parker-Holder +6 more
semanticscholar +1 more source
MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning [PDF]
International Conference on Learning Representations, 2023 Open-ended learning methods that automatically generate a curriculum of increasingly challenging tasks serve as a promising avenue toward generally capable reinforcement learning agents.
Mikayel Samvelyan +7 more
semanticscholar +1 more source
Stabilizing Unsupervised Environment Design with a Learned Adversary [PDF]
CoLLAs, 2023 A key challenge in training generally-capable agents is the design of training tasks that facilitate broad generalization and robustness to environment variations.
Ishita Mediratta +5 more
semanticscholar +1 more source
Discovering General Reinforcement Learning Algorithms with Adversarial Environment Design [PDF]
Neural Information Processing Systems, 2023 The past decade has seen vast progress in deep reinforcement learning (RL) on the back of algorithms manually designed by human researchers. Recently, it has been shown that it is possible to meta-learn update rules, with the hope of discovering ...
Matthew Jackson +7 more
semanticscholar +1 more source
Generalization through Diversity: Improving Unsupervised Environment Design [PDF]
International Joint Conference on Artificial Intelligence, 2023 Agent decision making using Reinforcement Learning (RL) heavily relies on either a model or simulator of the environment (e.g., moving in an 8x8 maze with three rooms, playing Chess on an 8x8 board).
Wenjun Li, Pradeep Varakantham, Dexun Li
semanticscholar +1 more source
Архитектон, 2022 The subject of the study is the specificity of the professional competence of an environment designer in the context of the convergence of science and art.
Petrashen Evgeniya P.
doaj +1 more source
Research on Key Pollutant Reduction Program of Environmental control in a Small River Basin of Guangxi [PDF]
E3S Web of Conferences, 2022 In order to strengthen the prevention and control of water pollution in rural rivers, it is necessary to analyze the pollution causes in detail, calculate the pollutant reduction amount and put forward the comprehensive treatment measures.
Song Haoyang +4 more
doaj +1 more source
Frontiers in Human Neuroscience, 2022 The introduction of Augmented Reality (AR) has attracted several developments, although the people’s experience of AR has not been clearly studied or contrasted with the human experience in 2D and 3D environments.
Carlos Andrés Mugruza-Vassallo +4 more
doaj +1 more source
Inpatient suicide in psychiatric settings: Evaluation of current prevention measures
Frontiers in Psychiatry, 2022 The risk of suicide in psychiatric hospitals is 50 times higher than in the general population, despite patient safety being a priority for any hospital.
Francesca Chammas +2 more
doaj +1 more source