# Model-Based Reinforcement Learning Exploits Passive Body Dynamics for High-Performance Biped Robot Locomotion

arXiv: https://arxiv.org/abs/2604.14565 · HTML: https://mlsanity.com/paper/2604.14565/

## 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 13 of its 40 references that are in the map.
- First posted on arXiv 16 Apr 2026.

## Placed in

- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 13 of 13)

- [Mastering Atari with Discrete World Models](https://mlsanity.com/paper/2010.02193/) (2020)
- [Recurrent World Models Facilitate Policy Evolution](https://mlsanity.com/paper/1809.01999/) (2018)
- [Learning agile and dynamic motor skills for legged robots](https://mlsanity.com/paper/1901.08652/) (2019)
- [DayDreamer: World Models for Physical Robot Learning](https://mlsanity.com/paper/2206.14176/) (2022)
- [A Survey of Embodied AI: From Simulators to Research Tasks](https://mlsanity.com/paper/2103.04918/) (2021)
- [Real-World Humanoid Locomotion with Reinforcement Learning](https://mlsanity.com/paper/2303.03381/) (2023)
- [ANYmal Parkour: Learning Agile Navigation for Quadrupedal Robots](https://mlsanity.com/paper/2306.14874/) (2023)
- [Learning-based Design and Control for Quadrupedal Robots with Parallel-Elastic Actuators](https://mlsanity.com/paper/2301.03509/) (2023)
- [Learning with Muscles: Benefits for Data-Efficiency and Robustness in Anthropomorphic Tasks](https://mlsanity.com/paper/2207.03952/) (2022)
- [DeepCPG Policies for Robot Locomotion](https://mlsanity.com/paper/2302.13191/) (2023)
- [Mechanical Intelligence Simplifies Control in Terrestrial Limbless Locomotion](https://mlsanity.com/paper/2304.08652/) (2023)
- [Effect of the Dynamics of a Horizontally Wobbling Mass on Biped Walking Performance](https://mlsanity.com/paper/2209.14515/) (2022)
- [Bipedal Robot Running: Human-like Actuation Timing Using Fast and Slow Adaptations](https://mlsanity.com/paper/2303.00910/) (2023)

## Abstract (arXiv)

Embodiment is a significant keyword in recent machine learning fields. This study focused on the passive nature of the body of a biped robot to generate walking and running locomotion using model-based deep reinforcement learning. We constructed two models in a simulator, one with passive elements (e.g., springs) and the other, which is similar to general humanoids, without passive elements. The training of the model with passive elements was highly affected by the attractor of the system. This lead that although the trajectories quickly converged to limit cycles, it took a long time to obtain large rewards. However, thanks to the attractor-driven learning, the acquired locomotion was robust and energy-efficient. The results revealed that robots with passive elements could efficiently acquire high-performance locomotion by utilizing stable limit cycles generated through dynamic interaction between the body and ground. This study demonstrates the importance of implementing passive properties in the body for future embodied AI.