MARLeME: A Multi-Agent Reinforcement Learning Model Extraction Library
This work addresses the need for better interpretability and safety in MARL systems, which is crucial for domains like security and critical decision-making, though it appears incremental as it builds on existing model extraction and symbolic modeling techniques.
The authors tackled the problem of improving explainability in multi-agent reinforcement learning (MARL) systems by introducing MARLeME, a library that approximates MARL with symbolic models, resulting in enhanced interpretability and verifiable behavior for safety-critical applications.
Multi-Agent Reinforcement Learning (MARL) encompasses a powerful class of methodologies that have been applied in a wide range of fields. An effective way to further empower these methodologies is to develop libraries and tools that could expand their interpretability and explainability. In this work, we introduce MARLeME: a MARL model extraction library, designed to improve explainability of MARL systems by approximating them with symbolic models. Symbolic models offer a high degree of interpretability, well-defined properties, and verifiable behaviour. Consequently, they can be used to inspect and better understand the underlying MARL system and corresponding MARL agents, as well as to replace all/some of the agents that are particularly safety and security critical.