24 papers · ranked by Valyu relevance
Krishnan Srinivasan, Benjamin Eysenbach, Sehoon Ha, Jie Tan + 1 more
'Chelsea Finn'] Safety is an essential component for deploying reinforcement learning (RL) algorithms in real-world scenarios, and is critical during the learning process itself. A natural first approach toward safe RL is to manually specify constraints on the policy's behavior. However, just as learning has enabled…
Dylan Slack, Yinlam Chow, Bo Dai, Nevan Wichers
Methods that extract policy primitives from offline demonstrations using deep generative models have shown promise at accelerating reinforcement learning (RL) for new tasks. Intuitively, these methods should also help to train safe RL agents because they enforce useful skills. However, we identify these techniques are…
Youngmin Kim, Richard Allmendinger, Manuel López‐Ibáñez
> Abstract Safe learning and optimization deals with learning and optimization problems that avoid, as much as possible, the evaluation of non-safe input points, which are solutions, policies, or strategies that cause an irrecoverable loss (e.g., breakage of a machine or equipment, or life threat). Although a…
Patrick A.F. Laing, Trevor Steward, Christopher G. Davey, Kim L. Felmingham + 6 more
Safety learning generates associative links between neutral stimuli and the absence of threat, promoting the inhibition of fear and security-seeking behaviours. Precisely how safety learning is mediated at the level of underlying brain systems, particularly in humans, remains unclear. Here, we integrated a novel…
Ekaterina Nikonova, Cheng Xue, Jochen Renz
During training, reinforcement learning systems interact with the world without considering the safety of their actions. When deployed into the real world, such systems can be dangerous and cause harm to their surroundings. Often, dangerous situations can be mitigated by defining a set of rules that the system should…
Hanping Zhang, Yuhong Guo
Safe Reinforcement Learning (Safe RL) aims to ensure safety when an RL agent conducts learning by interacting with real-world environments where improper actions can induce high costs or lead to severe consequences. In this paper, we propose a novel Safe Skill Planning (SSkP) approach to enhance effective safe RL by…
Cen-You Li, Marc Toussaint, Barbara Rakitsch, Christoph Zimmer
Neural Policies from Simulated Nonparametric Functions Authors: ['Cen-You Li' 'Marc Toussaint' 'Barbara Rakitsch' 'Christoph Zimmer'] Active Learning (AL) is a sequential learning approach aiming at selecting the most informative data for model training. In many systems, safety constraints appear during data…
Philip Hardie, Roisin O’Donovan, Suzi Jarvis, Catherine Redmond
Having psychological safety embedded in preceptorship relationships facilitates positive interpersonal and educational experiences for students. Psychological safety refers to a student’s belief as to whether or not it is safe for them to take interpersonal risks, such as asking questions, sharing an idea for…
Pranav Mahajan, Shuangyi Tong, Sang Wan Lee, Ben Seymour
The safety-efficiency dilemma describes the problem of maintaining safety during efficient exploration, and is a special case of the exploration-exploitation dilemma in the face of potentially catastrophic dangers. Conventional exploration-exploitation solutions collapse punishment and reward into a single signal…
Authors not listed
Realizing the promise of artificial intelligence (AI) to accelerate scientific progress and deliver technological impact depends on how effectively AI can be integrated into real-world decision- making processes. As Peter Norvig states, “Somewhat remarkably, almost all AI research until very recently has assumed that…
Pranav Mahajan, Ben Seymour
The seminal reward prediction error theory of dopamine function faces several key challenges. Most notable is the difficulty learning multiple rewards simultaneously, inefficient on-policy learning, and accounting for heterogeneous striatal responses in the tail of the striatum. We propose a normative framework, based…
Sahin Akdag, Zehra Altinay
This study aimed to evaluate the impact of digital stories in the learning-based themes of safe schools and to examine the perceptions of special educational needs in safe school environments. Training were carried out with informative videos created through the Distance Education and Information Technology Center…
Olusiji Adebola Lasekan, Margot Teresa Godoy Pena, Blessy Sarah Mathew
Early-childhood safety education is essential for reducing children’s vulnerability to everyday hazards, yet existing approaches remain fragmented and lack comprehensive pedagogical structure. This study integrates evidence from a systematic literature review (SLR) and media-based content analysis to develop a…
Dharanish Rajendra, Chaitanya S. Gokhale
Animals adapt their behaviour to current environmental conditions to enhance survival and reproductive success. While longterm adaptation occurs through evolutionary processes acting on heritable variation, individuals can also adapt within their lifetime via learning. Learning is particularly advantageous in…
Nicola Meda, Giovanni Frighetto, Aram Megighian, Mauro Agostino Zordan
Animals use pain-relief learning to discern which actions can diminish or abolish noxious stimuli. If relief from pain is provided in a specific location, place learning is the mechanism used to pinpoint that location in space. Little is known about how physiological and non-directly damaging stimuli can alter…
Feng Feng, Zhenru Chen, Jianyuan Ni, Yuanxun Zhang + 3 more
Drinking water is essential to public health and socioeconomic growth. Therefore, assessing and ensuring drinking water supply is a critical task in modern society. Conventional approaches to analyzing and controlling drinking water quality are labor-intensive and costly with a low throughput. Machine learning (ML) is…
Michelle F. Wright, Sandra T. Azar
Some researchers have implemented technologies to help overcome the barriers to reducing childhood injuries. Many of these technology-based injury prevention programs rely on individually tailored, written feedback to help improve parents’ knowledge of home safety. Serious game technologies might further aid in…
Joanna Bartnicka, Patrycja Kabiesz, Dorota Palka, Paulina Gajewska + 3 more
'Ejaz Ul Islam' 'Damian Szymanek' 'Paul B. Tchounwou'] With the advent of the COVID-19 pandemic, companies had to adapt quickly to survive in the market. During this time, employers played a key role, along with employees involved in Occupational Health and Safety (OHS) activities, as they were responsible for…
Camilla Kao, Che-I Kao, Russell Furr
In science, safety can seem unfashionable. Satisfying safety requirements can slow the pace of research, make it cumbersome, or cost significant amounts of money. The logic of rules can seem unclear. Compliance can feel like a negative incentive. So besides the obvious benefit that safety keeps one safe, why do some…
Camilla Kao, Che-I Kao, Russell Furr
In science, safety can seem unfashionable. Satisfying safety requirements can slow the pace of research, make it cumbersome, or cost significant amounts of money. The logic of rules can seem unclear. Compliance can feel like a negative incentive. So besides the obvious benefit that safety keeps one safe, why do some…
Camilla Kao, Che-I Kao, Russell Furr
In science, safety can seem unfashionable. Satisfying safety requirements can slow the pace of research, make it cumbersome, or cost significant amounts of money. The logic of rules can seem unclear. Compliance can feel like a negative incentive. So besides the obvious benefit that safety keeps one safe, why do some…
Camilla Kao, Che-I Kao, Russell Furr
In science, safety can seem unfashionable. Satisfying safety requirements can slow the pace of research, make it cumbersome, or cost significant amounts of money. The logic of rules can seem unclear. Compliance can feel like a negative incentive. So besides the obvious benefit that safety keeps one safe, why do some…
Juan Pimentel, Paola López, Camilo Correal, Anne Cockcroft + 1 more
'Neil Andersson'] Background Cultural safety training, whereby health professionals learn to reflect on their own culture and to respect the cultural identity of patients, could address intercultural tensions in health care. Given the context of their medical education, however, medical students might perceive such…
Camilla Kao, Che-I Kao
Recently we proposed that mission statements incorporating the concept of reducing uncertainty could provide a framework for learning the bread and depth of information that exists about health and safety. We briefly explained the definition of uncertainty in the context of health and safety, with the unifying…