# Think Smart, Act SMARL! Analyzing Probabilistic Logic Shields for Multi-Agent Reinforcement Learning

arXiv: https://arxiv.org/abs/2411.04867 · HTML: https://mlsanity.com/paper/2411.04867/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 46 references that are in the map.
- First posted on arXiv 7 Nov 2024.

## Builds on (most cited first, 23 of 23)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Rainbow: Combining Improvements in Deep Reinforcement Learning](https://mlsanity.com/paper/1710.02298/) (2017)
- [Safe Reinforcement Learning via Shielding](https://mlsanity.com/paper/1708.08611/) (2017)
- [Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving](https://mlsanity.com/paper/1610.03295/) (2016)
- [Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?](https://mlsanity.com/paper/2011.09533/) (2020)
- [Safe Multi-Agent Reinforcement Learning via Shielding](https://mlsanity.com/paper/2101.11196/) (2021)
- [Safe Reinforcement Learning via Shielding under Partial Observability](https://mlsanity.com/paper/2204.00755/) (2022)
- [Prosocial learning agents solve generalized Stag Hunts better than selfish ones](https://mlsanity.com/paper/1709.02865/) (2017)
- [Shield Synthesis: Runtime Enforcement for Reactive Systems](https://mlsanity.com/paper/1501.02573/) (2015)
- [Safe Reinforcement Learning via Probabilistic Logic Shields](https://mlsanity.com/paper/2303.03226/) (2023)
- [Reinforcement Learning for Market Making in a Multi-agent Dealer Market](https://mlsanity.com/paper/1911.05892/) (2019)
- [Verifiably Safe Exploration for End-to-End Reinforcement Learning](https://mlsanity.com/paper/2007.01223/) (2020)
- [MAMPS: Safe Multi-Agent Reinforcement Learning via Model Predictive Shielding](https://mlsanity.com/paper/1910.12639/) (2019)
- [Dynamic Model Predictive Shielding for Provably Safe Reinforcement Learning](https://mlsanity.com/paper/2405.13863/) (2024)
- [Dynamic Shielding for Reinforcement Learning in Black-Box Environments](https://mlsanity.com/paper/2207.13446/) (2022)
- [Model-based Dynamic Shielding for Safe and Efficient Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2304.06281/) (2023)
- [On the Semantics and Complexity of Probabilistic Logic Programs](https://mlsanity.com/paper/1701.09000/) (2017)
- [Healthcare Robotics](https://mlsanity.com/paper/1704.03931/) (2017)
- [Safe Multi-agent Reinforcement Learning with Natural Language Constraints](https://mlsanity.com/paper/2405.20018/) (2024)
- [A Neuro-Symbolic Approach to Multi-Agent RL for Interpretability and Probabilistic Decision Making](https://mlsanity.com/paper/2402.13440/) (2024)
- [Emergent Cooperation under Uncertain Incentive Alignment](https://mlsanity.com/paper/2401.12646/) (2024)

## Built on by (most cited first, 1 of 1)

- [PL-Guard: Probabilistic Logic Reasoning for LLM Guardrails](https://mlsanity.com/paper/2608.15673/) (2026)

## Abstract (arXiv)

Safe reinforcement learning (RL) is crucial for real-world applications, and multi-agent interactions introduce additional safety challenges. While Probabilistic Logic Shields (PLS) has been a powerful proposal to enforce safety in single-agent RL, their generalizability to multi-agent settings remains unexplored. In this paper, we address this gap by conducting extensive analyses of PLS within decentralized, multi-agent environments, and in doing so, propose Shielded Multi-Agent Reinforcement Learning (SMARL) as a general framework for steering MARL towards norm-compliant outcomes. Our key contributions are: (1) a novel Probabilistic Logic Temporal Difference (PLTD) update for shielded, independent Q-learning, which incorporates probabilistic constraints directly into the value update process; (2) a probabilistic logic policy gradient method for shielded PPO with formal safety guarantees for MARL; and (3) comprehensive evaluation across symmetric and asymmetrically shielded n-player game-theoretic benchmarks, demonstrating fewer constraint violations and significantly better cooperation under normative constraints. These results position SMARL as an effective mechanism for equilibrium selection, paving the way toward safer, socially aligned multi-agent systems.