An Abstraction-based Method to Check Multi-Agent Deep Reinforcement-Learning Behaviors

2021-02-02 · Pierre El Mqirmi, Francesco Belardinelli, Borja G. León

Multi-agent reinforcement learning (RL) often struggles to ensure the safe behaviours of the learning agents, and therefore it is generally not adapted to safety-critical applications. To address this issue, we present a methodology that combines formal verification with (deep) RL algorithms to guarantee the satisfaction of formally-specified safety constraints both in training and testing. The approach we propose expresses the constraints to verify in Probabilistic Computation Tree Logic (PCTL) and builds an abstract representation of the system to reduce the complexity of the verification step. This abstract model allows for model checking techniques to identify a set of abstract policies that meet the safety constraints expressed in PCTL. Then, the agents' behaviours are restricted according to these safe abstract policies. We provide formal guarantees that by using this method, the actions of the agents always meet the safety constraints, and provide a procedure to generate an abstract model automatically. We empirically evaluate and show the effectiveness of our method in a multi-agent environment.

📄 PDF Abstract BibTeX arXiv:2102.01434

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement LearningMulti-agent Reinforcement Learning reinforcement-learning Reinforcement Learning (RL)

Learning on Abstract Domains: A New Approach for Verifiable Guarantee in Reinforcement Learning

2021-06-13 · Peng Jin, Min Zhang, Jianwen Li, Li Han 외

Formally verifying Deep Reinforcement Learning (DRL) systems is a challenging task due to the dynamic continuity of system behaviors and the black-box feature of embedded neural networks. In this paper, we propose a nove…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning (RL)

Using Large Language Models for Abstraction of Planning Domains - Extended Version

2025-10-23 · Bita Banihashemi, Megh Patel, Yves Lespérance arxiv

Generating an abstraction of a dynamic domain that aligns with a given purpose remains a significant challenge given that the choice of such an abstraction can impact an agent's ability to plan, reason, and provide expla…

Explainable Multi-Agent Reinforcement Learning for Temporal Queries

2023-05-17 · Kayla Boggess, Sarit Kraus, Lu Feng

As multi-agent reinforcement learning (MARL) systems are increasingly deployed throughout society, it is imperative yet challenging for users to understand the emergent behaviors of MARL agents in complex environments. T…

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning

Brain-Inspired Planning for Better Generalization in Reinforcement Learning

2025-11-09 · Mingde "Harry" Zhao arxiv

Existing Reinforcement Learning (RL) systems encounter significant challenges when applied to real-world scenarios, primarily due to poor generalization across environments that differ from their training conditions. Thi…

Reinforcement Learning

Language as an Abstraction for Hierarchical Deep Reinforcement Learning

2019-06-18 · NeurIPS 2019 12 · Yiding Jiang, Shixiang Gu, Kevin Murphy, Chelsea Finn

Solving complex, temporally-extended tasks is a long-standing problem in reinforcement learning (RL). We hypothesize that one critical element of solving such problems is the notion of compositionality. With the ability …

Deep Reinforcement Learning Instruction Following MuJoCo Object+4