mlsanityData to 7 Oct 2026

Contrastive Explanations for Comparing Preferences of Reinforcement Learning Agents

arXiv 2112.09462 ↗First posted 17 Dec 2021cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

In complex tasks where the reward function is not straightforward and consists of a set of objectives, multiple reinforcement learning (RL) policies that perform task adequately, but employ different strategies can be trained by adjusting the impact of individual objectives on reward function. Understanding the differences in strategies between policies is necessary to enable users to choose between offered policies, and can help developers understand different behaviors that emerge from various reward functions and training hyperparameters in RL systems. In this work we compare behavior of two policies trained on the same task, but with different preferences in objectives. We propose a method for distinguishing between differences in behavior that stem from different abilities from those that are a consequence of opposing preferences of two RL agents. Furthermore, we use only data on preference-based differences in order to generate contrasting explanations about agents' preferences. Finally, we test and evaluate our approach on an autonomous driving task and compare the behavior of a safety-oriented policy and one that prefers speed.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 11 of its 19 references that are in the map. First posted on arXiv 17 Dec 2021.

Builds on

11 of 19 references.

References · 11

  1. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  2. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,201
  3. 2018Techniques for Interpretable Machine Learningcited by 237
  4. 2019Explainable Reinforcement Learning Through a Causal Lenscited by 177
  5. 2017Visualizing and Understanding Atari Agentscited by 141
  6. 2020Explainable Reinforcement Learning: A Surveycited by 139
  7. 2019Interestingness Elements for Explainable Reinforcement Learning: Understanding Agents' Capabilities and Limitationscited by 50
  8. 2018Contrastive Explanations for Reinforcement Learning in terms of Expected Consequencescited by 44
  9. 2017Enabling Robots to Communicate their Objectivescited by 34
  10. 2020Distal Explanations for Model-free Explainable Reinforcement Learningcited by 12
  11. 2018Autonomous Self-Explanation of Behavior for Interactive Reinforcement Learning Agentscited by 10

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 3.

5 papers.

  1. 2022Explainability in Deep Reinforcement Learning, a Review into Current Methods and Applicationscited by 6
  2. 2022ReCCoVER: Detecting Causal Confusion for Explainable Reinforcement Learningcited by 4
  3. 2023AutoDOViz: Human-Centered Automation for Decision Optimizationcited by 3
  4. 2023Towards Regulatable AI Systems: Technical Gaps and Policy Opportunitiescited by 2
  5. 2023Conveying Autonomous Robot Capabilities through Contrasting Behaviour Summariescited by 0