mlsanityData to 14 Oct 2026

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

arXiv 2411.04867 ↗First posted 7 Nov 2024cs.AI cs.LGcited by 1

Not on the map. Why?

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.

Key facts. Cited by 1 paper 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

23 of 46 references.

References · 23

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  4. 2017Rainbow: Combining Improvements in Deep Reinforcement Learningcited by 786
  5. 2017Safe Reinforcement Learning via Shieldingcited by 449
  6. 2016Safe, Multi-Agent, Reinforcement Learning for Autonomous Drivingcited by 311
  7. 2020Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?cited by 294
  8. 2021Safe Multi-Agent Reinforcement Learning via Shieldingcited by 61
  9. 2022Safe Reinforcement Learning via Shielding under Partial Observabilitycited by 56
  10. 2017Prosocial learning agents solve generalized Stag Hunts better than selfish onescited by 47
  11. 2015Shield Synthesis: Runtime Enforcement for Reactive Systemscited by 42
  12. 2023Safe Reinforcement Learning via Probabilistic Logic Shieldscited by 42
11 more
  1. 2019Reinforcement Learning for Market Making in a Multi-agent Dealer Marketcited by 39
  2. 2020Verifiably Safe Exploration for End-to-End Reinforcement Learningcited by 34
  3. 2019MAMPS: Safe Multi-Agent Reinforcement Learning via Model Predictive Shieldingcited by 20
  4. 2024Dynamic Model Predictive Shielding for Provably Safe Reinforcement Learningcited by 15
  5. 2022Dynamic Shielding for Reinforcement Learning in Black-Box Environmentscited by 11
  6. 2023Model-based Dynamic Shielding for Safe and Efficient Multi-Agent Reinforcement Learningcited by 11
  7. 2017On the Semantics and Complexity of Probabilistic Logic Programscited by 9
  8. 2017Healthcare Roboticscited by 9
  9. 2024Safe Multi-agent Reinforcement Learning with Natural Language Constraintscited by 7
  10. 2024A Neuro-Symbolic Approach to Multi-Agent RL for Interpretability and Probabilistic Decision Makingcited by 4
  11. 2024Emergent Cooperation under Uncertain Incentive Alignmentcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026PL-Guard: Probabilistic Logic Reasoning for LLM Guardrailscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Probabilistic Shielding for Safe Reinforcement Learning
  2. 2024Compositional Shielding and Reinforcement Learning for Multi-Agent Systems
  3. 2026Contract-Based Compositional Shielding for Safe Multi-Agent Reinforcement Learning
  4. 2026Robust Shielding for Safe Reinforcement Learning
  5. 2026Adaptive Probabilistic Shielding by Learning MDPs for Safe Reinforcement Learning
  6. 2025ProSh: Probabilistic Shielding for Model-free Reinforcement Learning
  7. 2026Robust Probabilistic Shielding for Safe Offline Reinforcement Learning
  8. 2026Decentralized Safe Multi-Agent Reinforcement Learning via Predictive Shielding