On the public citation graph

Advanced artificial agents intervene in the provision of reward

https://doi.org/10.1002/aaai.12064
0 signed · 52 inferred · view as graph

Inferred edges come from two machine sources: sweeps of open repository metadata (mostly SSRN and Zenodo), and a bulk OpenAlex citation snapshot. Every row below is labelled with the one it came from. Neither is a complete citation index — absence here is not evidence of absence.

Is this your work? Sign in with ORCID and put your name on the claims that are yours.
Claim with ORCID
Reference health. See whether every reference in this work resolves to a known work and none has been retracted — and get a dated CiteStamped badge you can embed.
See reference health

What this work says

Outgoing claims: the papers this work cites, builds on, or argues with.

inferredcites →https://doi.org/10.1007/978-3-319-41649-6_1openalex-snapshot
Self-Modification of Policy and Utility Function in Rational Agents
inferredcites →https://doi.org/10.1007/978-3-642-22887-2_2openalex-snapshot
Delusion, Survival, and Intelligent Agents
inferredcites →https://doi.org/10.1007/b138233openalex-snapshot
Universal Artificial Intellegence
inferredcites →https://doi.org/10.1007/s11229-021-03141-4openalex-snapshot
Reward tampering problems and solutions in reinforcement learning: a causal influence diagram perspective
inferredcites →https://doi.org/10.1093/oso/9780190905033.003.0013openalex-snapshot
Alignment for Advanced Machine Learning Systems
inferredcites →https://doi.org/10.1093/oso/9780198570509.003.0021openalex-snapshot
Artificial Intelligence as a positive and negative factor in global risk
inferredcites →https://doi.org/10.1126/science.127.3294.315openalex-snapshot
Self-Stimulation of the Brain
inferredcites →https://doi.org/10.1145/1015330.1015430openalex-snapshot
Apprenticeship learning via inverse reinforcement learning
inferredcites →https://doi.org/10.1609/aaai.v34i03.5628openalex-snapshot
Asymptotically Unambitious Artificial General Intelligence
inferredcites →https://doi.org/10.24963/ijcai.2017/32openalex-snapshot
The Off-Switch Game
inferredcites →https://doi.org/10.24963/ijcai.2017/662openalex-snapshot
Should Robots be Obedient?
inferredcites →https://doi.org/10.48550/arxiv.1606.03137openalex-snapshot
Cooperative Inverse Reinforcement Learning
inferredcites →https://doi.org/10.48550/arxiv.1609.05058openalex-snapshot
A Formal Solution to the Grain of Truth Problem
inferredcites →https://doi.org/10.48550/arxiv.1703.10284openalex-snapshot
Enter the Matrix: Safely Interruptible Autonomous Systems via Virtualization
inferredcites →https://doi.org/10.48550/arxiv.1704.02882openalex-snapshot
Dynamic Safe Interruptibility for Decentralized Multi-Agent Reinforcement Learning
inferredcites →https://doi.org/10.48550/arxiv.1805.11447openalex-snapshot
Virtuously Safe Reinforcement Learning
inferredcites →https://doi.org/10.48550/arxiv.1810.08575openalex-snapshot
Supervising strong learners by amplifying weak experts
inferredcites →https://doi.org/10.48550/arxiv.1906.01820openalex-snapshot
Risks from Learned Optimization in Advanced Machine Learning Systems
inferredcites →https://doi.org/10.48550/arxiv.2006.08753openalex-snapshot
Pessimism About Unknown Unknowns Inspires Conservatism
inferredcites →https://doi.org/10.48550/arxiv.2011.08820openalex-snapshot
REALab: An Embedded Perspective on Tampering
inferredcites →https://doi.org/10.5860/choice.187536openalex-snapshot
Superintelligence: paths, dangers, strategies
inferredcites →https://doi.org/10.5860/choice.187763openalex-snapshot
Stanford Encyclopedia of Philosophy

What points at this work

Incoming claims: where this work appears in other papers’ reference lists and arguments.

inferred← citeshttps://doi.org/10.2139/ssrn.4650168openalex-extracted
Towards a Humane AI Development Framework
inferred← citeshttps://doi.org/10.2139/ssrn.4666645openalex-extracted
Exploring the constraints on artificial general intelligence: a game-theoretic perspective
inferred← citeshttps://doi.org/10.2139/ssrn.4680247openalex-extracted
Exploring the Constraints on Artificial General Intelligence: A Game-Theoretic Perspective
inferred← citeshttps://doi.org/10.1002/aaai.70040openalex-snapshot
Imitation learning is probably existentially safe
inferred← citeshttps://doi.org/10.1007/978-3-031-65572-2_3openalex-snapshot
Computational Dualism and Objective Superintelligence
inferred← citeshttps://doi.org/10.1007/s11098-025-02343-7openalex-snapshot
AI welfare risks
inferred← citeshttps://doi.org/10.1007/s11245-023-09922-5openalex-snapshot
Artificial Intelligence and Autonomy: On the Ethical Dimension of Recommender Systems
inferred← citeshttps://doi.org/10.1007/s43681-023-00268-7openalex-snapshot
Symbiosis, not alignment, as the goal for liberal democracies in the transition to artificial general intelligence
inferred← citeshttps://doi.org/10.1007/s44163-026-01980-zopenalex-snapshot
A survey of reward hacking in agentic large language model systems
inferred← citeshttps://doi.org/10.1016/j.erss.2025.104167openalex-snapshot
Digitalization, autonomy and the future of energy policy
inferred← citeshttps://doi.org/10.1016/j.futures.2025.103563openalex-snapshot
Strategic insights from simulation gaming of AI race dynamics
inferred← citeshttps://doi.org/10.1016/j.mathsocsci.2024.03.004openalex-snapshot
Exploring the constraints on artificial general intelligence: A game-theoretic model of human vs machine interaction
inferred← citeshttps://doi.org/10.1093/oxfordhb/9780198940272.013.0006openalex-snapshot
The Challenges of Agentic AI Safety
inferred← citeshttps://doi.org/10.1109/icist59754.2023.10367162openalex-snapshot
Deep Reinforcement Learning for Unpredictability-Induced Rewards to Handle Spacecraft Landing
inferred← citeshttps://doi.org/10.1111/mila.12548openalex-snapshot
Against the Manhattan project framing of AI alignment
inferred← citeshttps://doi.org/10.15170/psk.2022.03.02.02openalex-snapshot
A bevonás új lehetőségei a 21. században: Az influencerek
inferred← citeshttps://doi.org/10.31219/osf.io/wexjropenalex-snapshot
Governance of a DAO for Facilitating Dialogue on Human-Algorithm Interaction and the Impact of Emerging Technologies on Society
inferred← citeshttps://doi.org/10.32604/cmc.2025.067750openalex-snapshot
Beyond Intentions: A Critical Survey of Misalignment in LLMs
inferred← citeshttps://doi.org/10.33293/1609-1442-2024-4(107)-7-32openalex-snapshot
Human in Economics and Human Economics
inferred← citeshttps://doi.org/10.33629/auhfd.1288894openalex-snapshot
MACHINA SAPIENS
inferred← citeshttps://doi.org/10.3390/fi15100336openalex-snapshot
Fluent but Not Factual: A Comparative Analysis of ChatGPT and Other AI Chatbots’ Proficiency and Originality in Scientific Writing for Humanities
inferred← citeshttps://doi.org/10.36227/techrxiv.19740190.v7openalex-snapshot
Computable Artificial General Intelligence
inferred← citeshttps://doi.org/10.36227/techrxiv.21965672.v4openalex-snapshot
Computational Dualism and Objective Superintelligence
inferred← citeshttps://doi.org/10.36227/techrxiv.21965672.v5openalex-snapshot
Computational Dualism and Objective Superintelligence
inferred← citeshttps://doi.org/10.36809/2309-9380-2024-43-9-13openalex-snapshot
Man in Digital Reality: Classification of Risks
inferred← citeshttps://doi.org/10.4324/9781003458333-39openalex-snapshot
The Civil Service and Artificial Intelligence
inferred← citeshttps://doi.org/10.48550/arxiv.2309.08636openalex-snapshot
ChatGPT v Bard v Bing v Claude 2 v Aria v human-expert. How good are AI chatbots at scientific writing?
inferred← citeshttps://doi.org/10.52825/scp.v4i.222openalex-snapshot
Challenges in Reward Design for Reinforcement Learning-based Traffic Signal Control: An Investigation using a CO2 Emission Objective
inferred← citeshttps://doi.org/10.5406/21521123.60.2.06openalex-snapshot
Value Alignment for Advanced Artificial Judicial Intelligence
inferred← citeshttps://doi.org/10.70777/si.v2i1.13799openalex-snapshot
Can a Bayesian Oracle Prevent Harm from an Agent?
Editorial review for independent work. ICSAC — the Institute for Complexity Science and Advanced Computing — runs a structured editorial panel for researchers publishing outside journals, and publishes on CiteStamp rails. Submission is free and goes through ORCID: icsacinstitute.org/submit.