Abstract
Reachability analysis is one of the most basic and challenging problems in verification. We investigate this problem in multi-agent reinforcement learning (MARL) system by transforming the reachability analysis to decision-making problem tackled by mixed integer linear programming (MILP) solver Gurobi. We define syntax and semantics for multi-role strategy logic (mrSL) which is used to describe the reachability specification. The logic mrSL is a variant of SL to express properties, which provide a holistic perspective to describe reachability properties instead of specifying a specific agent reaches a certain state in the MARL system. And the algorithms to translate reachability property into MILP constraints are provided. A tool called MAReachAnalysis is introduced, which uses Gurobi to solve the corresponding reachability problem and evaluate it on the predator-prey task of multi-agent deep deterministic policy gradient (MADDPG) example, discussion of the experimental results obtained on a range of test cases.
Highlights
As AI methods are increasingly used in safety-critical applications, concerns have been raised about the suitability of multi-agent reinforcement learning (MARL) for deployment in these applications
Specifications concerning strategic interplay based on roles naturally are required in verification. For this reason we put forward multi-role strategy logic(mrSL), which is a variant of the SL and provides a holistic perspective to describe some properties of the system, regardless of which agent is responsible for the concrete task
WORK With the deployment of systems based on MARL there has been a growing interest in their verification
Summary
As AI methods are increasingly used in safety-critical applications, concerns have been raised about the suitability of multi-agent reinforcement learning (MARL) for deployment in these applications. X. Wang et al.: Formal Reachability Analysis for MARL Systems competition among agents in order to achieve certain temporal goals, but it suffers from the strong limitation that strategies are treated only implicitly through modalities that refer to games between competing coalitions. Wang et al.: Formal Reachability Analysis for MARL Systems competition among agents in order to achieve certain temporal goals, but it suffers from the strong limitation that strategies are treated only implicitly through modalities that refer to games between competing coalitions To overcome this problem, SL is proposed in which strategies are explicitly referred to by using first-order quantifiers and bindings to agents. Specifications concerning strategic interplay based on roles naturally are required in verification For this reason we put forward multi-role strategy logic(mrSL), which is a variant of the SL and provides a holistic perspective to describe some properties of the system, regardless of which agent is responsible for the concrete task.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have