mlsanityData to 14 Oct 2026

An Interpretable Neural Control Network with Adaptable Online Learning for Sample Efficient Robot Locomotion Learning

arXiv 2501.10698 ↗First posted 18 Jan 2025cs.RO cs.LGcited by 0

On the map: Deep reinforcement learning methods → RL for robot locomotion and manipulation

Abstract (arXiv)

Robot locomotion learning using reinforcement learning suffers from training sample inefficiency and exhibits the non-understandable/black-box nature. Thus, this work presents a novel SME-AGOL to address such problems. Firstly, Sequential Motion Executor (SME) is a three-layer interpretable neural network, where the first produces the sequentially propagating hidden states, the second constructs the corresponding triangular bases with minor non-neighbor interference, and the third maps the bases to the motor commands. Secondly, the Adaptable Gradient-weighting Online Learning (AGOL) algorithm prioritizes the update of the parameters with high relevance score, allowing the learning to focus more on the highly relevant ones. Thus, these two components lead to an analyzable framework, where each sequential hidden state/basis represents the learned key poses/robot configuration. Compared to state-of-the-art methods, the SME-AGOL requires 40% fewer samples and receives 150% higher final reward/locomotion performance on a simulated hexapod robot, while taking merely 10 minutes of learning time from scratch on a physical hexapod robot. Taken together, this work not only proposes the SME-AGOL for sample efficient and understandable locomotion learning but also emphasizes the potential exploitation of interpretability for improving sample efficiency and learning performance.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods. Builds on 19 of its 46 references that are in the map. First posted on arXiv 18 Jan 2025.

Builds on

19 of 46 references.

References · 19

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  4. 2015Learning Deep Features for Discriminative Localizationcited by 2,436
  5. 2014Striving for Simplicity: The All Convolutional Netcited by 990
  6. 2021Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learningcited by 512
  7. 2022Rapid Locomotion via Reinforcement Learningcited by 168
  8. 2017Parameter Space Noise for Explorationcited by 161
  9. 2018Attention Branch Network: Learning of Attention Mechanism for Visual Explanationcited by 109
  10. 2021A Survey on Interpretable Reinforcement Learningcited by 73
  11. 2021Legged Robots that Keep on Learning: Fine-Tuning Locomotion Policies in the Real Worldcited by 71
  12. 2020Multi-expert learning of adaptive legged locomotioncited by 67
7 more
  1. 2023DreamWaQ: Learning Robust Quadrupedal Locomotion With Implicit Terrain Imagination via Deep Reinforcement Learningcited by 66
  2. 2020Deep Reinforcement Learning amidst Lifelong Non-Stationaritycited by 43
  3. 2020xAI-GAN: Enhancing Generative Adversarial Networks via Explainable AI Systemscited by 18
  4. 2024Fully Spiking Actor Network with Intra-layer Connections for Reinforcement Learningcited by 11
  5. 2020Learning to Walk: Spike Based Reinforcement Learning for Hexapod Robot Central Pattern Generationcited by 6
  6. 2023DeepCPG Policies for Robot Locomotioncited by 4
  7. 2024Experience-Learning Inspired Two-Step Reward Method for Efficient Legged Locomotion Learning Towards Natural and Robust Gaitscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Transferable Latent-to-Latent Locomotion Policy for Efficient and Versatile Motion Control of Diverse Legged Robots
  2. 2024Distilling Reinforcement Learning Policies for Interpretable Robot Locomotion: Gradient Boosting Machines and Symbolic Regression
  3. 2026Learning Loco-Manipulation From SMPC Demonstrations With Sparse Offline-to-Online RL
  4. 2024An Efficient Model-Based Approach on Learning Agile Motor Skills without Reinforcement
  5. 2025MA-ROESL: Motion-aware Rapid Reward Optimization for Efficient Robot Skill Learning from Single Videos ↗
  6. 2025Pretraining in Actor-Critic Reinforcement Learning for Locomotion
  7. 2023A Real-World Quadrupedal Locomotion Benchmark for Offline Reinforcement Learning
  8. 2025Learning More With Less: Sample Efficient Model-Based RL for Loco-Manipulation