Promptable behaviors: Personalizing multi-objective rewards from human preferences
Customizing robotic behaviors to be aligned with diverse human preferences is an
underexplored challenge in the field of embodied AI. In this paper we present Promptable …
underexplored challenge in the field of embodied AI. In this paper we present Promptable …
Reinforcement Learning and Machine ethics: a systematic review
Machine ethics is the field that studies how ethical behaviour can be accomplished by
autonomous systems. While there exist some systematic reviews aiming to consolidate the …
autonomous systems. While there exist some systematic reviews aiming to consolidate the …
Multi-objective multi-agent deep reinforcement learning to reduce bus bunching for multiline services with a shared corridor
Bus bunching is a long-standing problem in transit operation and ruining the regularity of
transit service. In a typical urban transit network setting of multiple lines with a shared …
transit service. In a typical urban transit network setting of multiple lines with a shared …
[HTML][HTML] Monte carlo tree search-based deep reinforcement learning for flexible operation & maintenance optimization of a nuclear power plant
Nuclear power plants (NPPs) are required to operate on a flexible profitable production plan
while guaranteeing high safety standards. Deep reinforcement learning (DRL) is an effective …
while guaranteeing high safety standards. Deep reinforcement learning (DRL) is an effective …
[PDF][PDF] Modeling moral choices in social dilemmas with multi-agent reinforcement learning
E Tennant, S Hailes, M Musolesi - Proceedings of the Thirty-Second …, 2023 - cris.unibo.it
Abstract Practical uses of Artificial Intelligence (AI) in the real world have demonstrated the
importance of embedding moral choices into intelligent agents. They have also highlighted …
importance of embedding moral choices into intelligent agents. They have also highlighted …
Towards Bidirectional Human-AI Alignment: A Systematic Review for Clarifications, Framework, and Future Directions
Recent advancements in general-purpose AI have highlighted the importance of guiding AI
systems towards the intended goals, ethical principles, and values of individuals and …
systems towards the intended goals, ethical principles, and values of individuals and …
Building altruistic and moral ai agent with brain-inspired affective empathy mechanisms
F Zhao, H Feng, H Tong, Z Han, E Lu, Y Sun… - arXiv preprint arXiv …, 2024 - arxiv.org
As AI closely interacts with human society, it is crucial to ensure that its decision-making is
safe, altruistic, and aligned with human ethical and moral values. However, existing …
safe, altruistic, and aligned with human ethical and moral values. However, existing …
MOMAland: A Set of Benchmarks for Multi-Objective Multi-Agent Reinforcement Learning
Many challenging tasks such as managing traffic systems, electricity grids, or supply chains
involve complex decision-making processes that must balance multiple conflicting …
involve complex decision-making processes that must balance multiple conflicting …
Multi-objective Reinforcement Learning: A Tool for Pluralistic Alignment
Reinforcement learning (RL) is a valuable tool for the creation of AI systems. However it may
be problematic to adequately align RL based on scalar rewards if there are multiple …
be problematic to adequately align RL based on scalar rewards if there are multiple …
Evolutionary multi-objective deep reinforcement learning for autonomous UAV navigation in large-scale complex environments
G An, Z Wu, Z Shen, K Shang, H Ishibuchi - Proceedings of the Genetic …, 2023 - dl.acm.org
Autonomous navigation of Unmanned Aerial Vehicles (UAVs) in large-scale complex
environments presents a significant challenge in modern aerospace engineering, as it …
environments presents a significant challenge in modern aerospace engineering, as it …