Strongly-Typed Agents are Guaranteed to Interact Safely
As artificial agents proliferate, it is becoming increasingly important to ensure that their interactions with one another are well-behaved. In this paper, we formalize a common-sense notion of when algorithms are well-behaved: an algorithm is safe if it does no harm. Motivated by recent progress in deep learning, we focus on the specific case where agents update their actions according to gradient descent. The paper shows that that gradient descent converges to a Nash equilibrium in safe games. The main contribution is to define strongly-typed agents and show they are guaranteed to interact safely, thereby providing sufficient conditions to guarantee safe interactions. A series of examples show that strong-typing generalizes certain key features of convexity, is closely related to blind source separation, and introduces a new perspective on classical multilinear games based on tensor decomposition.
Code (0)
등록된 구현이 없습니다.
Tasks
blind source separationCommon Sense ReasoningTensor DecompositionSimilar Papers 제목 키워드 기반
Strongly-Typed Recurrent Neural Networks
Recurrent neural networks are increasing popular models for sequential learning. Unfortunately, although the most effective RNN architectures are perhaps excessively complicated, extensive searches have not found simpler…
Autonomous Capability Assessment of Sequential Decision-Making Systems in Stochastic Settings (Extended Version)
It is essential for users to understand what their AI systems can and can't do in order to use them safely. However, the problem of enabling users to assess AI systems with sequential decision-making (SDM) capabilities i…
Active LearningDecision MakingSequential Decision MakingAutonomous Capability Assessment of Sequential Decision-Making Systems in Stochastic Settings
It is essential for users to understand what their AI systems can and can't do in order to use them safely. However, the problem of enabling users to assess AI systems with sequential decision-making (SDM) capabilities i…
Web Agents Should Use Typed Actions Instead of Click-Based Browsing
This position paper argues that building a reliable agentic Web requires shifting from low-level interaction primitives to typed actions supported by a semantic layer. Today's web agents primarily operate through clicks,…
Don't Start What You Can't Finish: A Counterfactual Audit of Support-State Triage in LLM Agents
Current agent evaluations largely reward execution on fully specified tasks, while recent work studies clarification [11, 22, 2], capability awareness [9, 1], abstention [8, 14], and search termination [20, 5] mostly in …