Results 41 to 50 of about 277,892 (265)
Safe In-Context Reinforcement Learning
CoRRIn-context reinforcement learning (ICRL) is an emerging RL paradigm where an agent, after pretraining, can adapt to out-of-distribution test tasks without any parameter updates, instead relying on an expanding context of interaction history. While ICRL has shown impressive generalization, safety during this adaptation process remains unexplored ...
Amir Moeini +6 more
openaire +3 more sources
Annals of Clinical and Translational Neurology, EarlyView.ABSTRACT Objective Digital technologies hold promise for transforming healthcare by enhancing personalized treatments and offer valuable opportunities to improve patient care. Here, we evaluated several novel, self‐administered, home‐based, digital endpoints for their association with corresponding conventional standard clinical measures (primary) in ...
Arne Mueller +14 more
wiley +1 more source
Imagine to Ensure Safety in Hierarchical Reinforcement Learning
Machine Learning and Knowledge ExtractionThis work investigates the safe exploration problem in reinforcement learning, where an agent must maximize cumulative performance while simultaneously satisfying safety constraints.
Gregory Gorbov +2 more
doaj +1 more source
Annals of Clinical and Translational Neurology, EarlyView.ABSTRACT Objective Facioscapulohumeral muscular dystrophy (FSHD) is one of the most debilitating and common muscular dystrophies. Despite its severity, no approved therapy exists for FSHD patients. However, several therapeutic candidates are currently under development, and some have recently entered clinical trials, marking the need for reliable ...
Mustafa Bilal Bayazit +11 more
wiley +1 more source
Human neurocomputational mechanisms of guilt-driven and shame-driven altruistic behavior
eLifeAlthough prior research has examined the psychological and neural correlates of guilt and shame, the cognitive antecedents that trigger them, as well as their transformation into social behavior, remain insufficiently understood.
Ruida Zhu +6 more
doaj +1 more source
Annals of Clinical and Translational Neurology, EarlyView.ABSTRACT Objective Treatment of disorders of consciousness (DoC) remains a major clinical challenge, and noninvasive, targeted modulation of deep brain structures has emerged as a promising therapeutic strategy. We aimed to evaluate the feasibility/safety and preliminary effects of thalamic temporal interference stimulation (TIS) targeting centromedian‐
Gengyao Hu +7 more
wiley +1 more source
Shields for Safe Reinforcement Learning
Communications of the ACMReinforcement learning (RL) is a prominent machine learning technique used to optimize an agent’s performance in potentially unknown environments. Despite its popularity and success, RL lacks safety guarantees, both during the learning phase and deployment.
Bettina Könighofer +4 more
openaire +4 more sources
Anytime Safe Reinforcement Learning
CoRRThis paper considers the problem of solving constrained reinforcement learning problems with anytime guarantees, meaning that the algorithmic solution returns a safe policy regardless of when it is terminated. Drawing inspiration from anytime constrained optimization, we introduce Reinforcement Learning-based Safe Gradient Flow (RL-SGF), an on ...
Pol Mestres +2 more
openaire +3 more sources
Arthritis Care &Research, Accepted Article.Objective Reproductive‐age women with systemic autoimmune and rheumatic diseases (SARDs) have unique information needs related to their SARDs and reproductive health. We sought to understand their use of and receptivity to current and hypothetical generative artificial intelligence (AI) tools for health information‐seeking. Methods We conducted a cross‐
Mariam Arif +5 more
wiley +1 more source
Structure Learning for Safe Policy Improvement [PDF]
Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, 2019 We investigate how Safe Policy Improvement (SPI) algorithms can exploit the structure of factored Markov decision processes when such structure is unknown a priori. To facilitate the application of reinforcement learning in the real world, SPI provides probabilistic guarantees that policy changes in a running process will improve the performance of ...
Thiago D. Simão, Matthijs T. J. Spaan
openaire +2 more sources