Avoiding negative side effects due to incomplete knowledge of AI systems
Autonomous agents acting in the real-world often operate based on models that ignore
certain aspects of the environment. The incompleteness of any given model–handcrafted or …
certain aspects of the environment. The incompleteness of any given model–handcrafted or …
Avoiding negative side effects of autonomous systems in the open world
Autonomous systems that operate in the open world often use incomplete models of their
environment. Model incompleteness is inevitable due to the practical limitations in precise …
environment. Model incompleteness is inevitable due to the practical limitations in precise …
Planning and learning for non-markovian negative side effects using finite state controllers
A Srivastava, S Saisubramanian, P Paruchuri… - Proceedings of the …, 2023 - ojs.aaai.org
Autonomous systems are often deployed in the open world where it is hard to obtain
complete specifications of objectives and constraints. Operating based on an incomplete …
complete specifications of objectives and constraints. Operating based on an incomplete …
Challenges for using impact regularizers to avoid negative side effects
D Lindner, K Matoba, A Meulemans - arXiv preprint arXiv:2101.12509, 2021 - arxiv.org
Designing reward functions for reinforcement learning is difficult: besides specifying which
behavior is rewarded for a task, the reward also has to discourage undesired outcomes …
behavior is rewarded for a task, the reward also has to discourage undesired outcomes …
Defining and Identifying the Legal Culpability of Side Effects Using Causal Graphs
H Ashton - CEUR Workshop Proceedings, 2022 - discovery.ucl.ac.uk
Deployed algorithms can cause certain negative side effects on the world in pursuit of their
objective. It is important to define precisely what an algorithmic side-effect is in a way which …
objective. It is important to define precisely what an algorithmic side-effect is in a way which …
Mitigating Negative Side Effects in Multi-Agent Systems Using Blame Assignment
P Rustagi, S Saisubramanian - arXiv preprint arXiv:2405.04702, 2024 - arxiv.org
When agents that are independently trained (or designed) to complete their individual tasks
are deployed in a shared environment, their joint actions may produce negative side effects …
are deployed in a shared environment, their joint actions may produce negative side effects …
Safe Deep Neural Networks
KM Matoba - 2024 - infoscience.epfl.ch
The capabilities of deep learning systems have advanced much faster than our ability to
understand them. Whilst the gains from deep neural networks (DNNs) are significant, they …
understand them. Whilst the gains from deep neural networks (DNNs) are significant, they …
[PDF][PDF] Mitigating Negative Side Effects
A Srivastava - 2023 - cdn.iiit.ac.in
Autonomous systems perform various tasks across different industries ranging from finance
to healthcare to space applications. However, these systems are often deployed in the open …
to healthcare to space applications. However, these systems are often deployed in the open …
Reliable Decision-Making with Imprecise Models
S Saisubramanian - 2022 - scholarworks.umass.edu
The rapid growth in the deployment of autonomous systems across various sectors has
generated considerable interest in how these systems can operate reliably in large …
generated considerable interest in how these systems can operate reliably in large …
[PDF][PDF] Identifying Missing Features in State Representation for Safe Decision-Making
The advancement of AI has enabled high-level automation in complex environments.
However, autonomous systems in the real-world may act in an unsafe manner when there …
However, autonomous systems in the real-world may act in an unsafe manner when there …