paper-with-me

Papers

Value Alignment Verification

2020-12-02 · Daniel S. Brown, Jordan Schneider, Anca D. Dragan, Scott Niekum

As humans interact with autonomous agents to perform increasingly complicated, potentially risky tasks, it is important to be able to efficiently evaluate an agent's performance and correctness. In this paper we formalize and theoretically analyze the problem of efficient value alignment verification: how to efficiently test whether the behavior of another agent is aligned with a human's values. The goal is to construct a kind of "driver's test" that a human can give to any agent which will verify value alignment via a minimal number of queries. We study alignment verification problems with both idealized humans that have an explicit reward function as well as problems where they have implicit values. We analyze verification of exact value alignment for rational agents and propose and analyze heuristic and approximate value alignment verification tests in a wide range of gridworlds and a continuous autonomous driving domain. Finally, we prove that there exist sufficient conditions such that we can verify exact and approximate alignment across an infinite set of test environments via a constant-query-complexity alignment test.

📄 PDF Abstract BibTeX arXiv:2012.01557

Code (1)

dsbrown1331/vav-icml 공식 구현

Tasks

Autonomous Driving

Similar Papers 제목 키워드 기반

Value Alignment Verification

2020-10-16 · NeurIPS Workshop HAMLETS 2020 12 · Anonymous

As humans interact with autonomous agents to perform increasingly complicated, potentially risky tasks, it is important that humans can verify these agents' trustworthiness and efficiently evaluate their performance and …

Autonomous Driving

Hybrid Sequence Modeling and Reinforced Verification for Controllable Target-Conditioned Decision Making

2025-08-22 · Yue Pei, Hongming Zhang, Chao Gao, Martin Müller 외 arxiv

Target-conditioned sequence models provide a simple interface for controllable offline decision making, but the requested target return can be an unreliable control signal, especially when the target return lies in under…

Decision Making

Scalable Synthesis of Formally Verified Neural Value Function for Hamilton-Jacobi Reachability Analysis

2024-07-30 · Yujie Yang, Hanjiang Hu, Tianhao Wei, Shengbo Eben Li 외

Hamilton-Jacobi (HJ) reachability analysis provides a formal method for guaranteeing safety in constrained control problems. It synthesizes a value function to represent a long-term safe set called feasible region. Early…

Expected Value Alignment for Generative Reward Modeling in Formal Mathematics Verification

2026-05-31 · Shihao Ji, Haotao Tan, Zihui Song, Mingyu Li arxiv

Large Language Models (LLMs) are increasingly used with formal interactive theorem provers such as Lean 4. Scaling these systems with reinforcement learning or search methods requires process reward models (PRMs) that ca…

Reinforcement Learning

The Shadow Self: Intrinsic Value Misalignment in Large Language Model Agents

2026-01-24 · Chen Chen, Kim Young Il, Yuan Yang, Wenhao Su 외 arxiv

Large language model (LLM) agents with extended autonomy unlock new capabilities, but also introduce heightened challenges for LLM safety. In particular, an LLM agent may pursue objectives that deviate from human values …