Adaptive GR(1) Specification Repair for Liveness-Preserving Shielding in Reinforcement Learning

arXiv:2511.02605v3 Announce Type: replace Abstract: Shielding is widely used to enforce safety in reinforcement learning (RL), ensuring that an agent's actions remain compliant with formal specifications. Classical shielding approaches, however, are often static, in the sense that they assume fixed logical specifications and hand-crafted abstractions. While these static shields provide safety under nominal assumptions, they fail to adapt when environment assumptions are violated. In this paper, we develop an adaptive shielding framework based on based on Generalized Reactivity of rank 1 (GR(1)) specifications, a tractable and expressive fragment of Linear Temporal Logic (LTL) that captures both safety and liveness properties. Our method detects environment assumption violations at runtime and employs Inductive Logic Programming (ILP) to automatically repair GR(1) specifications online, in a systematic and interpretable way. This ensures that the shield evolves gracefully, ensuring liveness is achievable and minimally weakening goals only when necessary. We consider two case studies: Minepump and Atari Seaquest; showing that (i) static symbolic controllers are often severely suboptimal when optimizing for auxiliary rewards, and (ii) RL agents equipped with our adaptive shield maintain near-optimal reward and perfect logical compliance compared with static shields.

Abstract:Shielding is widely used to enforce safety in reinforcement learning (RL), ensuring that an agent's actions remain compliant with formal specifications. Classical shielding approaches, however, are often static, in the sense that they assume fixed logical specifications and hand-crafted abstractions. While these static shields provide safety under nominal assumptions, they fail to adapt when environment assumptions are violated. In this paper, we develop an adaptive shielding framework based on based on Generalized Reactivity of rank 1 (GR(1)) specifications, a tractable and expressive fragment of Linear Temporal Logic (LTL) that captures both safety and liveness properties. Our method detects environment assumption violations at runtime and employs Inductive Logic Programming (ILP) to automatically repair GR(1) specifications online, in a systematic and interpretable way. This ensures that the shield evolves gracefully, ensuring liveness is achievable and minimally weakening goals only when necessary. We consider two case studies: Minepump and Atari Seaquest; showing that (i) static symbolic controllers are often severely suboptimal when optimizing for auxiliary rewards, and (ii) RL agents equipped with our adaptive shield maintain near-optimal reward and perfect logical compliance compared with static shields.

Artificial Intelligence (cs.AI)

arXiv:2511.02605 [cs.AI]

(or arXiv:2511.02605v3 [cs.AI] for this version)

From: Alexander W. Goodall [view email] [v1] Tue, 4 Nov 2025 14:27:28 UTC (1,169 KB) [v2] Fri, 20 Feb 2026 17:44:58 UTC (1,134 KB) [v3] Mon, 24 Aug 2026 20:59:41 UTC (1,117 KB)

analiza aiqbench

Adaptive GR(1) Specification Repair for Liveness-Preserving Shielding in Reinforcement Learning

Subiecte conexe