Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Enabling MCTS Explainability for Sequential Planning Through Computation Tree Logic

Ziyan An, Hendrik Baier, Abhishek Dubey, Ayan Mukhopadhyay, Meiyi Ma

TL;DR

This paper considers the use of MCTS in transportation routing services, where the algorithm is integrated to develop optimized route plans, and introduces a novel computation tree logic-based explainer for MCTS.

Abstract

Monte Carlo tree search (MCTS) is one of the most capable online search algorithms for sequential planning tasks, with significant applications in areas such as resource allocation and transit planning. Despite its strong performance in real-world deployment, the inherent complexity of MCTS makes it challenging to understand for users without technical background. This paper considers the use of MCTS in transportation routing services, where the algorithm is integrated to develop optimized route plans. These plans are required to meet a range of constraints and requirements simultaneously, further complicating the task of explaining the algorithm's operation in real-world contexts. To address this critical research gap, we introduce a novel computation tree logic-based explainer for MCTS. Our framework begins by taking user-defined requirements and translating them into rigorous logic specifications through the use of language templates. Then, our explainer incorporates a logic verification and quantitative evaluation module that validates the states and actions traversed by the MCTS algorithm. The outcomes of this analysis are then rendered into human-readable descriptive text using a second set of language templates. The user satisfaction of our approach was assessed through a survey with 82 participants. The results indicated that our explanatory approach significantly outperforms other baselines in user preference.

Enabling MCTS Explainability for Sequential Planning Through Computation Tree Logic

TL;DR

This paper considers the use of MCTS in transportation routing services, where the algorithm is integrated to develop optimized route plans, and introduces a novel computation tree logic-based explainer for MCTS.

Abstract

Monte Carlo tree search (MCTS) is one of the most capable online search algorithms for sequential planning tasks, with significant applications in areas such as resource allocation and transit planning. Despite its strong performance in real-world deployment, the inherent complexity of MCTS makes it challenging to understand for users without technical background. This paper considers the use of MCTS in transportation routing services, where the algorithm is integrated to develop optimized route plans. These plans are required to meet a range of constraints and requirements simultaneously, further complicating the task of explaining the algorithm's operation in real-world contexts. To address this critical research gap, we introduce a novel computation tree logic-based explainer for MCTS. Our framework begins by taking user-defined requirements and translating them into rigorous logic specifications through the use of language templates. Then, our explainer incorporates a logic verification and quantitative evaluation module that validates the states and actions traversed by the MCTS algorithm. The outcomes of this analysis are then rendered into human-readable descriptive text using a second set of language templates. The user satisfaction of our approach was assessed through a survey with 82 participants. The results indicated that our explanatory approach significantly outperforms other baselines in user preference.
Paper Structure (33 sections, 1 equation, 7 figures, 3 tables, 3 algorithms)

This paper contains 33 sections, 1 equation, 7 figures, 3 tables, 3 algorithms.

Table of Contents

  1. CTL-Based Explainable MCTS
  2. Formulating User Queries
  3. CTL Verification and Quantitative Evaluation
  4. Mapping Queries to CTL Formulas
  5. Factual Queries --- "Why?"
  6. Contrastive Queries --- "Why Not?"
  7. Queries with Tree Expansion --- "What If?"
  8. Generating Natural Language Explanations
  9. Evaluation
  10. Study Design
  11. Testing Environment.
  12. Participants.
  13. Explanations Quality Assessment
  14. Evaluation Metrics.
  15. Baselines.
  16. ...and 18 more sections

Figures (7)

  • Figure 1: Illustration of the complete explanation process.
  • Figure 2: Illustration of different types of queries.
  • Figure 3: Comparative analysis across five scenarios (S1-S5). Blue bars represent baseline 1 with map visualization; green bars represent baseline 2 with search tree visualization; and red bars represent the proposed approach. Plot (a) displays the aggregated results across all scenarios.
  • Figure 4: User preferences based on technical background
  • Figure 5: An example of the survey scenarios.
  • ...and 2 more figures

Theorems & Definitions (1)

  • Definition 1: Syntax of CTL formulas