Optimality-based reward learning with applications to toxicology
SJ Weisenthal, M Eckard, A Ertefaie… - arXiv preprint arXiv …, 2024 - arxiv.org
In toxicology research, experiments are often conducted to determine the effect of toxicant
exposure on the behavior of mice, where mice are randomized to receive the toxicant or not …
exposure on the behavior of mice, where mice are randomized to receive the toxicant or not …
[图书][B] Relative Sparsity and Optimality-Based Reward Learning With Applications to Medical Decisions and Toxicology
SJ Weisenthal - 2023 - search.proquest.com
Existing statistical methods can be used to estimate a policy, or a mapping from covariates to
decisions, which can then instruct decision makers (eg, whether to administer hypotension …
decisions, which can then instruct decision makers (eg, whether to administer hypotension …
Inferring learning rules from animal decision-making
How do animals learn? This remains an elusive question in neuroscience. Whereas
reinforcement learning often focuses on the design of algorithms that enable artificial agents …
reinforcement learning often focuses on the design of algorithms that enable artificial agents …
Scaling laws for reward model overoptimization
In reinforcement learning from human feedback, it is common to optimize against a reward
model trained to predict human preferences. Because the reward model is an imperfect …
model trained to predict human preferences. Because the reward model is an imperfect …
Model-based reinforcement learning under concurrent schedules of reinforcement in rodents
N Huh, S Jo, H Kim, JH Sul, MW Jung - Learning & Memory, 2009 - learnmem.cshlp.org
Reinforcement learning theories postulate that actions are chosen to maximize a long-term
sum of positive outcomes based on value functions, which are subjective estimates of future …
sum of positive outcomes based on value functions, which are subjective estimates of future …
[HTML][HTML] Computational mechanisms underlying motivation to earn symbolic reinforcers
Reinforcement learning (RL) is a theoretical framework that describes how agents learn to
select options that maximize rewards and minimize punishments over time. We often make …
select options that maximize rewards and minimize punishments over time. We often make …
Computational mechanisms underlying motivation to earn symbolic reinforcers
Reinforcement learning is a theoretical framework that describes how agents learn to select
options that maximize rewards and minimize punishments over time. We often make …
options that maximize rewards and minimize punishments over time. We often make …
How fast to work: Response vigor, motivation and tonic dopamine
Reinforcement learning models have long promised to unify computational, psychological
and neural accounts of appetitively conditioned behavior. However, the bulk of data on …
and neural accounts of appetitively conditioned behavior. However, the bulk of data on …
[PDF][PDF] Reinforcement Learning Leads to Risk Averse Behavior
JC Denrell - Proceedings of the Annual Meeting of the Cognitive …, 2008 - escholarship.org
Animals and humans often have to choose between options with reward distributions that
are initially unknown and can only be learned through experience. Recent experimental and …
are initially unknown and can only be learned through experience. Recent experimental and …
[PDF][PDF] Expressing non-Markov reward to a Markov agent
Abstract Markov Decision Processes are the standard model of sequential decision-making
problems in reinforcement learning. However, as noted by Abel et al.[1], for some …
problems in reinforcement learning. However, as noted by Abel et al.[1], for some …