mlsanityData to 14 Oct 2026

Symbolic Explanation of Affinity-Based Reinforcement Learning Agents with Markov Models

arXiv 2208.12627 ↗First posted 26 Aug 2022cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

The proliferation of artificial intelligence is increasingly dependent on model understanding. Understanding demands both an interpretation - a human reasoning about a model's behavior - and an explanation - a symbolic representation of the functioning of the model. Notwithstanding the imperative of transparency for safety, trust, and acceptance, the opacity of state-of-the-art reinforcement learning algorithms conceals the rudiments of their learned strategies. We have developed a policy regularization method that asserts the global intrinsic affinities of learned strategies. These affinities provide a means of reasoning about a policy's behavior, thus making it inherently interpretable. We have demonstrated our method in personalized prosperity management where individuals' spending behavior in time dictate their investment strategies, i.e. distinct spending personalities may have dissimilar associations with different investment classes. We now explain our model by reproducing the underlying prototypical policies with discretized Markov models. These global surrogates are symbolic representations of the prototypical policies.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 35 references that are in the map. First posted on arXiv 26 Aug 2022.

Builds on

21 of 35 references.

References · 21

  1. 2015Continuous control with deep reinforcement learningcited by 3,407
  2. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,552
  3. 2017Reinforcement Learning with Deep Energy-Based Policiescited by 669
  4. 2015Risk-Constrained Reinforcement Learning with Percentile Risk Criteriacited by 337
  5. 2019Explainable Reinforcement Learning Through a Causal Lenscited by 177
  6. 2018State Representation Learning for Control: An Overviewcited by 127
  7. 2020Explainability in Deep Reinforcement Learningcited by 97
  8. 2019A survey on intrinsic motivation in reinforcement learningcited by 81
  9. 2021AI in Finance: Challenges, Techniques and Opportunitiescited by 81
  10. 2019Reinforcement Learning with Convex Constraintscited by 60
  11. 2017Hybrid Reward Architecture for Reinforcement Learningcited by 58
  12. 2019Information asymmetry in KL-regularized RLcited by 53
9 more
  1. 2019Dot-to-Dot: Explainable Hierarchical Reinforcement Learning for Robotic Manipulationcited by 35
  2. 2021Towards Hierarchical Task Decomposition using Deep Reinforcement Learning for Pick and Place Subtaskscited by 14
  3. 2015Statistical and Computational Guarantees for the Baum-Welch Algorithmcited by 11
  4. 2022Reinforcement Learning Your Way: Agent Characterization through Policy Regularizationcited by 6
  5. 2022Can Interpretable Reinforcement Learning Manage Prosperity Your Way?cited by 6
  6. 2022Collaborative Training of Heterogeneous Reinforcement Learning Agents in Environments with Sparse Rewards: What and When to Share?cited by 4
  7. 2022Policy Regularization for Legible Behaviorcited by 3
  8. 2021Explainable AI for Psychological Profiling from Digital Footprints: A Case Study of Big Five Personality Predictions from Spending Datacited by 2
  9. 2022Reinforcement Learning with Intrinsic Affinity for Personalized Prosperity Managementcited by 1

Built on by

Not cited yet.