# Requirement-Based Testing: Enhancing Reinforcement Learning with Game Theory

arXiv: https://arxiv.org/abs/2407.18994 · HTML: https://mlsanity.com/paper/2407.18994/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL training of language and agent models, one of 15 directions in Deep reinforcement learning methods.
- Builds on 3 of its 50 references that are in the map.
- First posted on arXiv 26 Jul 2024.

## Placed in

- Deep reinforcement learning methods / [RL training of language and agent models](https://mlsanity.com/deeprl/rl-training-of-language-and-agent-models/)

## Builds on (most cited first, 3 of 3)

- [Deep Reinforcement Learning for Black-Box Testing of Android Apps](https://mlsanity.com/paper/2101.02636/) (2021)
- [AbsSynthe: abstract synthesis from succinct safety specifications](https://mlsanity.com/paper/1407.5961/) (2014)
- [Reusable Formal Verification of DAG-based Consensus Protocols](https://mlsanity.com/paper/2407.02167/) (2024)

## Abstract (arXiv)

We consider the automatic online synthesis of black-box test cases from functional requirements specified as automata for reactive implementations. The goal of the tester is to reach some given state, so as to satisfy a coverage criterion, while monitoring the violation of the requirements. We develop an approach based on Monte Carlo Tree Search, which is a classical technique in reinforcement learning for efficiently selecting promising inputs. Seeing the automata requirements as a game between the implementation and the tester, we develop a heuristic by biasing the search towards inputs that are promising in this game. We experimentally show that our heuristic accelerates the convergence of the Monte Carlo Tree Search algorithm, thus improving the performance of testing.