mlsanityData to 14 Oct 2026

Entropy-Controlled Intrinsic Motivation Reinforcement Learning for Quadruped Robot Locomotion in Complex Terrains

arXiv 2512.06486 ↗First posted 6 Dec 2025cs.ROcited by 0

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

Abstract (arXiv)

Learning is the basis of both biological and artificial systems when it comes to mimicking intelligent behaviors. From the classical PPO (Proximal Policy Optimization), there is a series of deep reinforcement learning algorithms which are widely used in training locomotion policies for quadrupedal robots because of their stability and sample efficiency. However, among all these variants, experiments and simulations often converge prematurely, leading to suboptimal locomotion and reduced task performance. Therefore, in this paper, we introduce Entropy-Controlled Intrinsic Motivation (ECIM), an entropy-based reinforcement learning algorithm in contrast with the PPO series, that can reduce premature convergence by combining intrinsic motivation with adaptive exploration. For experiments, in order to parallel with other baselines, we chose to apply it in Isaac Gym across six terrain categories: upward slopes, downward slopes, uneven rough terrain, ascending stairs, descending stairs, and flat ground as widely used. For comparison, our experiments consistently achieve better performance: task rewards increase by 4--12%, peak body pitch oscillation is reduced by 23--29%, joint acceleration decreases by 20--32%, and joint torque consumption declines by 11--20%. Overall, our model ECIM, by combining entropy control and intrinsic motivation control, achieves better results in stability across different terrains for quadrupedal locomotion, and at the same time reduces energetic cost and makes it a practical choice for complex robotic control tasks.

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 11 of its 34 references that are in the map. First posted on arXiv 6 Dec 2025.

Builds on

11 of 34 references.

References · 11

  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. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 2,026
  4. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 998
  5. 2018Exploration by Random Network Distillationcited by 993
  6. 2020Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 721
  7. 2016Unifying Count-Based Exploration and Intrinsic Motivationcited by 639
  8. 2021Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learningcited by 512
  9. 2016Safe, Multi-Agent, Reinforcement Learning for Autonomous Drivingcited by 311
  10. 2018Residual Reinforcement Learning for Robot Controlcited by 274
  11. 2018Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Controlcited by 230

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Neuromorphic Reinforcement Learning for Quadruped Locomotion Control on Uneven Terrain
  2. 2024Constrained Intrinsic Motivation for Reinforcement Learning
  3. 2022Energy-based Legged Robots Terrain Traversability Modeling via Deep Inverse Reinforcement Learning
  4. 2025PALo: Learning Posture-Aware Locomotion for Quadruped Robots
  5. 2025Learning to Walk With Less: A Dyna-Style Approach to Quadrupedal Locomotion
  6. 2025Jump-Start Reinforcement Learning with Self-Evolving Priors for Extreme Monopedal Locomotion
  7. 2025Motion Priors Reimagined: Adapting Flat-Terrain Skills for Complex Quadruped Mobility
  8. 2025Quadruped Robot Simulation Using Deep Reinforcement Learning -- A step towards locomotion policy