Autonomous Self-Explanation of Behavior for Interactive Reinforcement Learning Agents
Not on the map. Why?
Abstract (arXiv)
In cooperation, the workers must know how co-workers behave. However, an agent's policy, which is embedded in a statistical machine learning model, is hard to understand, and requires much time and knowledge to comprehend. Therefore, it is difficult for people to predict the behavior of machine learning robots, which makes Human Robot Cooperation challenging. In this paper, we propose Instruction-based Behavior Explanation (IBE), a method to explain an autonomous agent's future behavior. In IBE, an agent can autonomously acquire the expressions to explain its own behavior by reusing the instructions given by a human expert to accelerate the learning of the agent's policy. IBE also enables a developmental agent, whose policy may change during the cooperation, to explain its own behavior with sufficient time granularity.
Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). First posted on arXiv 20 Oct 2018.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 4; 2022: 1; 2023: 3; 2024: 2.
10 papers.
- 2021A Survey on Interpretable Reinforcement Learningcited by 73
- 2023Explainable Deep Reinforcement Learning: State of the Art and Challengescited by 33
- 2023Explainable Reinforcement Learning via a Causal World Modelcited by 22
- 2021Explainable Autonomous Robots: A Survey and Perspectivecited by 15
- 2021Contrastive Explanations for Comparing Preferences of Reinforcement Learning Agentscited by 5
- 2022A Survey on Explainable Reinforcement Learning: Concepts, Algorithms, Challengescited by 3
- 2023Explainable Goal Recognition: A Framework Based on Weight of Evidencecited by 3
- 2024XRL-Bench: A Benchmark for Evaluating and Comparing Explainable Reinforcement Learning Techniquescited by 2
- 2021One-shot Policy Elicitation via Semantic Reward Manipulationcited by 1
- 2024Continual Adversarial Reinforcement Learning (CARL) of False Data Injection detection: forgetting and explainabilitycited by 0
- 2024Continual Adversarial Reinforcement Learning (CARL) of False Data Injection detection: forgetting and explainability15 Nov 2024
- 2024XRL-Bench: A Benchmark for Evaluating and Comparing Explainable Reinforcement Learning Techniques20 Feb 2024
- 2023Explainable Reinforcement Learning via a Causal World Model4 May 2023
- 2023Explainable Goal Recognition: A Framework Based on Weight of Evidence9 Mar 2023
- 2023Explainable Deep Reinforcement Learning: State of the Art and Challenges24 Jan 2023
- 2022A Survey on Explainable Reinforcement Learning: Concepts, Algorithms, Challenges12 Nov 2022
- 2021A Survey on Interpretable Reinforcement Learning24 Dec 2021
- 2021Contrastive Explanations for Comparing Preferences of Reinforcement Learning Agents17 Dec 2021
- 2021Explainable Autonomous Robots: A Survey and Perspective6 May 2021
- 2021One-shot Policy Elicitation via Semantic Reward Manipulation6 Jan 2021