اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدPersonalization in Human-AI Teams: Improving the Compatibility-Accuracy Tradeoff
64
0
0.0
(
0
)
تأليف
Jonathan Martinez
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
AI systems that model and interact with users can update their models over time to reflect new information and changes in the environment. Although these updates may improve the overall performance of the AI system, they may actually hurt the performance with respect to individual users. Prior work has studied the trade-off between improving the systems accuracy following an update and the compatibility of the updated system with prior user experience. The more the model is forced to be compatible with a prior version, the higher loss in accuracy it will incur. In this paper, we show that by personalizing the loss function to specific users, in some cases it is possible to improve the compatibility-accuracy trade-off with respect to these users (increase the compatibility of the model while sacrificing less accuracy). We present experimental results indicating that this approach provides moderate improvements on average (around 20%) but large improvements for certain users (up to 300%).
قيم البحث
اقرأ أيضاً
While we would like agents that can coordinate with humans, current algorithms such as self-play and population-based training create agents that can coordinate with themselves. Agents that assume their partner to be optimal or similar to them can co
nverge to coordination protocols that fail to understand and be understood by humans. To demonstrate this, we introduce a simple environment that requires challenging coordination, based on the popular game Overcooked, and learn a simple model that mimics human play. We evaluate the performance of agents trained via self-play and population-based training. These agents perform very well when paired with themselves, but when paired with our human model, they are significantly worse than agents designed to play with the human model. An experiment with a planning algorithm yields the same conclusion, though only when the human-aware planner is given the exact human model that it is playing with. A user study with real humans shows this pattern as well, though less strongly. Qualitatively, we find that the gains come from having the agent adapt to the humans gameplay. Given this result, we suggest several approaches for designing agents that learn about humans in order to better coordinate with them. Code is available at https://github.com/HumanCompatibleAI/overcooked_ai.
One of the key challenges when developing a predictive model is the capability to describe the domain knowledge and the cause-effect relationships in a simple way. Decision rules are a useful and important methodology in this context, justifying thei
r application in several areas, in particular in clinical practice. Several machine-learning classifiers have exploited the advantageous properties of decision rules to build intelligent prediction models, namely decision trees and ensembles of trees (ETs). However, such methodologies usually suffer from a trade-off between interpretability and predictive performance. Some procedures consider a simplification of ETs, using heuristic approaches to select an optimal reduced set of decision rules. In this paper, we introduce a novel step to those methodologies. We create a new component to predict if a given rule will be correct or not for a particular patient, which introduces personalization into the procedure. Furthermore, the validation results using three public clinical datasets show that it also allows to increase the predictive performance of the selected set of rules, improving the mentioned trade-off.
How to attribute responsibility for autonomous artificial intelligence (AI) systems actions has been widely debated across the humanities and social science disciplines. This work presents two experiments ($N$=200 each) that measure peoples perceptio
ns of eight different notions of moral responsibility concerning AI and human agents in the context of bail decision-making. Using real-life adapted vignettes, our experiments show that AI agents are held causally responsible and blamed similarly to human agents for an identical task. However, there was a meaningful difference in how people perceived these agents moral responsibility; human agents were ascribed to a higher degree of present-looking and forward-looking notions of responsibility than AI agents. We also found that people expect both AI and human decision-makers and advisors to justify their decisions regardless of their nature. We discuss policy and HCI implications of these findings, such as the need for explainable AI in high-stakes scenarios.
Adversarial training augments the training set with perturbations to improve the robust error (over worst-case perturbations), but it often leads to an increase in the standard error (on unperturbed test inputs). Previous explanations for this tradeo
ff rely on the assumption that no predictor in the hypothesis class has low standard and robust error. In this work, we precisely characterize the effect of augmentation on the standard error in linear regression when the optimal linear predictor has zero standard and robust error. In particular, we show that the standard error could increase even when the augmented perturbations have noiseless observations from the optimal linear predictor. We then prove that the recently proposed robust self-training (RST) estimator improves robust error without sacrificing standard error for noiseless linear regression. Empirically, for neural networks, we find that RST with different adversarial training methods improves both standard and robust error for random and adversarial rotations and adversarial $ell_infty$ perturbations in CIFAR-10.
Deep reinforcement learning has generated superhuman AI in competitive games such as Go and StarCraft. Can similar learning techniques create a superior AI teammate for human-machine collaborative games? Will humans prefer AI teammates that improve o
bjective team performance or those that improve subjective metrics of trust? In this study, we perform a single-blind evaluation of teams of humans and AI agents in the cooperative card game Hanabi, with both rule-based and learning-based agents. In addition to the game score, used as an objective metric of the human-AI team performance, we also quantify subjective measures of the humans perceived performance, teamwork, interpretability, trust, and overall preference of AI teammate. We find that humans have a clear preference toward a rule-based AI teammate (SmartBot) over a state-of-the-art learning-based AI teammate (Other-Play) across nearly all subjective metrics, and generally view the learning-based agent negatively, despite no statistical difference in the game score. This result has implications for future AI design and reinforcement learning benchmarking, highlighting the need to incorporate subjective metrics of human-AI teaming rather than a singular focus on objective task performance.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
