mlsanityData to 14 Oct 2026

SkillTree: Explainable Skill-Based Deep Reinforcement Learning for Long-Horizon Control Tasks

arXiv 2411.12173 ↗First posted 19 Nov 2024cs.LG cs.AIcited by 3

On the map: Deep reinforcement learning methods → Interpretable and logic-guided RL

Abstract (arXiv)

Deep reinforcement learning (DRL) has achieved remarkable success in various research domains. However, its reliance on neural networks results in a lack of transparency, which limits its practical applications. To achieve explainability, decision trees have emerged as a popular and promising alternative to neural networks. Nonetheless, due to their limited expressiveness, traditional decision trees struggle with high-dimensional long-horizon continuous control tasks. In this paper, we proposes SkillTree, a novel framework that reduces complex continuous action spaces into discrete skill spaces. Our hierarchical approach integrates a differentiable decision tree within the high-level policy to generate skill embeddings, which subsequently guide the low-level policy in executing skills. By making skill decisions explainable, we achieve skill-level explainability, enhancing the understanding of the decision-making process in complex tasks. Experimental results demonstrate that our method achieves performance comparable to skill-based neural networks in complex robotic arm control domains. Furthermore, SkillTree offers explanations at the skill level, thereby increasing the transparency of the decision-making process.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Interpretable and logic-guided RL, one of 15 directions in Deep reinforcement learning methods. Builds on 28 of its 45 references that are in the map. First posted on arXiv 19 Nov 2024.

Builds on

28 of 45 references.

References · 28

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  2. 2017Neural Discrete Representation Learningcited by 4,712
  3. 2020D4RL: Datasets for Deep Data-Driven Reinforcement Learningcited by 1,427
  4. 2021CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Taskscited by 584
  5. 2019Learning Latent Plans from Playcited by 316
  6. 2017Distilling a Neural Network Into a Soft Decision Treecited by 236
  7. 2020Accelerating Reinforcement Learning with Learned Skill Priorscited by 223
  8. 2018Verifiable Reinforcement Learning via Policy Extractioncited by 177
  9. 2019Explainable Reinforcement Learning Through a Causal Lenscited by 177
  10. 2017Visualizing and Understanding Atari Agentscited by 141
  11. 2020Explainability in Deep Reinforcement Learningcited by 97
  12. 2018SDRL: Interpretable and Data-efficient Deep Reinforcement Learning Leveraging Symbolic Planningcited by 78
16 more
  1. 2017Hierarchical and Interpretable Skill Acquisition in Multi-task Reinforcement Learningcited by 77
  2. 2021Demonstration-Guided Reinforcement Learning with Learned Skillscited by 76
  3. 2018Toward Interpretable Deep Reinforcement Learning with Linear Model U-Treescited by 65
  4. 2021Accelerating Robotic Reinforcement Learning via Parameterized Action Primitivescited by 65
  5. 2018TACO: Learning Task Decomposition via Temporal Alignment for Controlcited by 62
  6. 2020Learning Robot Skills with Temporal Variational Inferencecited by 54
  7. 2017Interpretable Policies for Reinforcement Learning by Genetic Programmingcited by 48
  8. 2021Counterfactual State Explanations for Reinforcement Learning Agents via Generative Deep Learningcited by 39
  9. 2019Explaining Reinforcement Learning to Mere Mortals: An Empirical Studycited by 21
  10. 2020TripleTree: A Versatile Interpretable Representation of Black Box Agents and their Environmentscited by 18
  11. 2020CDT: Cascading Decision Trees for Explainable Reinforcement Learningcited by 15
  12. 2020Visual Navigation in Real-World Indoor Environments Using End-to-End Deep Reinforcement Learningcited by 14
  13. 2019Mo"ET: Mixture of Expert Trees and its Application to Verifiable Reinforcement Learningcited by 12
  14. 2021Learning Symbolic Rules for Interpretable Deep Reinforcement Learningcited by 9
  15. 2020Interpretable Rule Discovery Through Bilevel Optimization of Split-Rules of Nonlinear Decision Trees for Classification Problemscited by 4
  16. 2023Synthesizing Programmatic Policies with Actor-Critic Algorithms and ReLU Networkscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026E2DT: Efficient and Effective Decision Transformer with Experience-Aware Sampling for Robotic Manipulationcited by 0
  2. 2026ConceptTree: Bringing Semantic Transparency to Black-Box Decision Making for Robotic Manipulationcited by 0
  3. 2026Safe Task Planning with Long-Term Graph Memory for Embodied Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Putting the Iterative Training of Decision Trees to the Test on a Real-World Robotic Task
  2. 2024Optimizing Interpretable Decision Tree Policies for Reinforcement Learning
  3. 2024Solving Offline Reinforcement Learning with Decision Tree Regression
  4. 2024Robust Policy Learning via Offline Skill Diffusion
  5. 2026Boosting Deep Reinforcement Learning with Semantic Knowledge for Robotic Manipulators
  6. 2024EXTRACT: Efficient Policy Learning by Extracting Transferable Robot Skills from Offline Data
  7. 2022Learning Interpretable, High-Performing Policies for Autonomous Driving
  8. 2024Distill2Explain: Differentiable decision trees for explainable reinforcement learning in energy application controllers