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

by   Pierre El Mqirmi, et al.

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.



There are no comments yet.


page 1

page 2

page 3

page 4


Safe Multi-Agent Reinforcement Learning via Shielding

Multi-agent reinforcement learning (MARL) has been increasingly used in ...

Synthesizing Safe Policies under Probabilistic Constraints with Reinforcement Learning and Bayesian Model Checking

In this paper we propose Policy Synthesis under probabilistic Constraint...

On Assessing The Safety of Reinforcement Learning algorithms Using Formal Methods

The increasing adoption of Reinforcement Learning in safety-critical sys...

Probabilistic Guarantees for Safe Deep Reinforcement Learning

Deep reinforcement learning has been successfully applied to many contro...

"I'm sorry Dave, I'm afraid I can't do that" Deep Q-learning from forbidden action

The use of Reinforcement Learning (RL) is still restricted to simulation...

Formal Methods with a Touch of Magic

Machine learning and formal methods have complimentary benefits and draw...

Verified Probabilistic Policies for Deep Reinforcement Learning

Deep reinforcement learning is an increasingly popular technique for syn...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.