Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 10, 2025Journal of Artificial Intelligence ResearchOpen Access

Causal Explanations for Sequential Decision Making

View Full Paper
Ask AI
Bookmark
Share

Authors

SNSamer B. NashedSMSaaduddin MahmudCGClaudia V. Goldman

Discussion

Loading...

Member takes

Overview

This framework generates causal explanations for agent behavior in sequential decision-making, highlighting benefits over Shapley-value methods.

Key Points

  • The framework enables semantically distinct explanations for agent actions, enhancing user understanding.
  • Causal inference methods were developed within the structural causal model, supporting novel comparison metrics.
  • User studies demonstrate preferences for explanations generated by our framework versus state-of-the-art systems.
  • MeanRESP offers flexibility with various approximations while managing computational demands and sample complexity.

Cite This Study

Nashed et al. (2025) studied this question.

synapsesocial.com/papers/68c1a25a54b1d3bfb60dd030https://doi.org/10.1613/jair.1.18126
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Explain It as Simple as Possible, but No Simpler – Explanation via Model Simplification for Addressing Inferential Gap (Abstract Reprint)2025
  2. 2Generating Causal Explanations of Vehicular Agent Behavioural Interactions with Learnt Reward Profiles2025
  3. 3Extending Structural Causal Models for Use in Autonomous Embodied Systems2024
  4. 4Counterfactual Language Reasoning for Explainable Recommendation Systems2025 · 1 citations
  5. 5CONSTRUCTION OF PROBABILISTIC CAUSAL RELATIONSHIPS BETWEEN EQUIVALENCE CLASSES OF DATA IN AN INTELLIGENT INFORMATION SYSTEM2024