mlsanityData to 7 Oct 2026

Beyond Value: CHECKLIST for Testing Inferences in Planning-Based RL

arXiv 2206.02039 ↗First posted 4 Jun 2022cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Reinforcement learning (RL) agents are commonly evaluated via their expected value over a distribution of test scenarios. Unfortunately, this evaluation approach provides limited evidence for post-deployment generalization beyond the test distribution. In this paper, we address this limitation by extending the recent CheckList testing methodology from natural language processing to planning-based RL. Specifically, we consider testing RL agents that make decisions via online tree search using a learned transition model and value function. The key idea is to improve the assessment of future performance via a CheckList approach for exploring and assessing the agent's inferences during tree search. The approach provides the user with an interface and general query-rule mechanism for identifying potential inference flaws and validating expected inference invariances. We present a user study involving knowledgeable AI researchers using the approach to evaluate an agent trained to play a complex real-time strategy game. The results show the approach is effective in allowing users to identify previously-unknown flaws in the agent's reasoning. In addition, our analysis provides insight into how AI experts use this type of testing approach, which may help improve future instantiations.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 21 of its 29 references that are in the map. First posted on arXiv 4 Jun 2022.

Builds on

21 of 29 references.

References · 21

  1. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,327
  2. 2020Beyond Accuracy: Behavioral Testing of NLP models with CheckListcited by 979
  3. 2019Model-Based Reinforcement Learning for Ataricited by 495
  4. 2019Emergent Tool Use From Multi-Agent Autocurriculacited by 308
  5. 2019Adversarial Policies: Attacking Deep Reinforcement Learningcited by 209
  6. 2018Programmatically Interpretable Reinforcement Learningcited by 192
  7. 2019Explainable Reinforcement Learning Through a Causal Lenscited by 177
  8. 2017Visualizing and Understanding Atari Agentscited by 141
  9. 2020Explainable Reinforcement Learning: A Surveycited by 139
  10. 2020Explainability in Deep Reinforcement Learningcited by 96
  11. 2019Towards Interpretable Reinforcement Learning Using Attention Augmented Agentscited by 82
  12. 2018Towards Accountable AI: Hybrid Human-Machine Analyses for Characterizing System Failurecited by 49
9 more
  1. 2018Contrastive Explanations for Reinforcement Learning in terms of Expected Consequencescited by 44
  2. 2020The Emerging Landscape of Explainable AI Planning and Decision Makingcited by 44
  3. 2017Explainable Planningcited by 40
  4. 2018Learning Finite State Representations of Recurrent Policy Networkscited by 37
  5. 2020Understanding the Power and Limitations of Teaching with Imperfect Knowledgecited by 23
  6. 2021Why? Why not? When? Visual Explanations of Agent Behavior in Reinforcement Learningcited by 16
  7. 2020Contrastive Explanations for Reinforcement Learning via Embedded Self Predictionscited by 13
  8. 2021Visualizing MuZero Modelscited by 9
  9. 2021Identifying Reasoning Flaws in Planning-Based RL Using Tree Explanationscited by 2

Built on by

Not cited yet.