mlsanityData to 14 Oct 2026

SMOSE: Sparse Mixture of Shallow Experts for Interpretable Reinforcement Learning in Continuous Control Tasks

arXiv 2412.13053 ↗First posted 17 Dec 2024cs.LG cs.AIcited by 3

On the map: Deep reinforcement learning methods → Deep RL algorithms and representations

Abstract (arXiv)

Continuous control tasks often involve high-dimensional, dynamic, and non-linear environments. State-of-the-art performance in these tasks is achieved through complex closed-box policies that are effective, but suffer from an inherent opacity. Interpretable policies, while generally underperforming compared to their closed-box counterparts, advantageously facilitate transparent decision-making within automated systems. Hence, their usage is often essential for diagnosing and mitigating errors, supporting ethical and legal accountability, and fostering trust among stakeholders. In this paper, we propose SMOSE, a novel method to train sparsely activated interpretable controllers, based on a top-1 Mixture-of-Experts architecture. SMOSE combines a set of interpretable decisionmakers, trained to be experts in different basic skills, and an interpretable router that assigns tasks among the experts. The training is carried out via state-of-the-art Reinforcement Learning algorithms, exploiting load-balancing techniques to ensure fair expert usage. We then distill decision trees from the weights of the router, significantly improving the ease of interpretation. We evaluate SMOSE on six benchmark environments from MuJoCo: our method outperforms recent interpretable baselines and narrows the gap with noninterpretable state-of-the-art algorithms

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 21 of its 41 references that are in the map. First posted on arXiv 17 Dec 2024.

Builds on

21 of 41 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Mixtures of Experts Unlock Parameter Scaling for Deep RL13 Feb

Other references · 20

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  3. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
  4. 2021Scaling Vision with Sparse Mixture of Expertscited by 747
  5. 2021Interpretable Machine Learning: Fundamental Principles and 10 Grand Challengescited by 367
  6. 2018Programmatically Interpretable Reinforcement Learningcited by 193
  7. 2018Verifiable Reinforcement Learning via Policy Extractioncited by 177
  8. 2021A Survey on Interpretable Reinforcement Learningcited by 73
  9. 2018The age of secrecy and unfairness in recidivism predictioncited by 53
  10. 2019Neural Logic Reinforcement Learningcited by 53
  11. 2016On the Safety of Machine Learning: Cyber-Physical Systems, Decision Sciences, and Data Productscited by 52
  12. 2022A Comparative Study of Faithfulness Metrics for Model Interpretability Methodscited by 39
8 more
  1. 2021Neuro-Symbolic Reinforcement Learning with First-Order Logiccited by 30
  2. 2019Conservative Q-Improvement: Reinforcement Learning for an Interpretable Decision-Tree Policycited by 29
  3. 2021Probabilistic Mixture-of-Experts for Efficient Deep Reinforcement Learningcited by 27
  4. 2023Hierarchical Programmatic Reinforcement Learning via Learning to Compose Programscited by 20
  5. 2024Interpretable and Editable Programmatic Tree Policies for Reinforcement Learningcited by 18
  6. 2020Evolutionary learning of interpretable decision treescited by 15
  7. 2023Interpretable Reinforcement Learning for Robotics and Continuous Controlcited by 5
  8. 2024EXPIL: Explanatory Predicate Invention for Learning in Gamescited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025A Comprehensive Survey of Mixture-of-Experts: Algorithms, Theory, and Applicationscited by 91
  2. 2026REFLEX: Reflective Evolution from LLM Experiencecited by 2
  3. 2026Topology-Aware Revival for Efficient Sparse Trainingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Interpretable reinforcement learning with decision-tree pruning
  2. 2026Phase-Aware Mixture of Experts for Agentic Reinforcement Learning
  3. 2025Mastering Massive Multi-Task Reinforcement Learning via Mixture-of-Expert Decision Transformer
  4. 2025Mixture-of-Experts Meets In-Context Reinforcement Learning
  5. 2026Structuring MoE Expert Selection for Agentic Reinforcement Learning
  6. 2025Towards Stable and Effective Reinforcement Learning for Mixture-of-Experts
  7. 2019Mo"ET: Mixture of Expert Trees and its Application to Verifiable Reinforcement Learning
  8. 2025Mixture of Autoencoder Experts Guidance using Unlabeled and Incomplete Data for Exploration in Reinforcement Learning