Research map / Learning theory and algorithms / Prediction and decision losses
Rethinking Safe Control in the Presence of Self-Seeking Humans
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use the proposed risk-constrained strategy selection and adaptive policy instead of DWSC or MSNE | Autonomous agents interacting with self-seeking humans · Type A | risk and total reward | Helped |
| Use the proposed risk-constrained strategy selection and adaptive policy instead of DWSC or MSNE | Autonomous agents interacting with self-seeking humans · Type B | reward-risk trade-off | Helped |
| Use the proposed risk-constrained strategy selection and adaptive policy instead of DWSC or MSNE | Autonomous agents interacting with self-seeking humans · Type C | reward-risk trade-off | Mixed |
| Use the proposed risk-constrained strategy selection and adaptive policy instead of DWSC or MSNE | Autonomous agents interacting with self-seeking humans · Type D | risk and total reward | No clear effect |
| Always choose the cooperative intention (π^a=1) as in DWSC | Autonomous agents with mixed human strategy dynamics · Type A and Type C | risk | Hurt |
| Always choose the cooperative intention (π^a=1) as in DWSC | Autonomous agents with mixed human strategy dynamics · Type A | human cooperation probability: 0.9 -> 0 | Hurt |
| Restrict strategies to the reward-based mixed-strategy Nash equilibrium | Equilibrium-based stochastic methods · Type C and Type D | risk | Hurt |
| Restrict strategies to the reward-based mixed-strategy Nash equilibrium | Equilibrium-based stochastic methods · All four interaction types | reward and risk optimality | Hurt |
Closest papers by meaning
- From Gambits to Assurances: Game-Theoretic Integration of Safety and Learning for Interactive Robotics (AAAI 2025 · similarity 0.86)
- Risk-Sensitive Theory of Mind: Coordinating with Agents of Unknown Bias using Cumulative Prospect Theory (ICML 2025 · similarity 0.85)
- Instrumental Choices: Measuring the Propensity of LLM Agents to Pursue Instrumental Behaviors (NeurIPS 2026 · similarity 0.84)
- Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents (ICLR 2026 · similarity 0.84)
- Regulating AI: Applying Insights from Behavioural Economics and Psychology to the Application of Article 5 of the EU AI Act (AAAI 2024 · similarity 0.84)
- Emergent Risk Awareness in Rational Agents under Resource Constraints (NeurIPS 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.