# HuMam: Humanoid Motion Control via End-to-End Deep Reinforcement Learning with Mamba

arXiv: https://arxiv.org/abs/2509.18046 · HTML: https://mlsanity.com/paper/2509.18046/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Video, motion and generative Mamba models, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 20 of its 34 references that are in the map.
- First posted on arXiv 22 Sep 2025.

## Placed in

- State-space sequence models (S4, Mamba) / [Video, motion and generative Mamba models](https://mlsanity.com/ssm/video-motion-and-generative-mamba-models/)
- 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, 20 of 20)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [Learning Quadrupedal Locomotion over Challenging Terrain](https://mlsanity.com/paper/2010.11251/) (2020)
- [Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning](https://mlsanity.com/paper/2109.11978/) (2021)
- [RMA: Rapid Motor Adaptation for Legged Robots](https://mlsanity.com/paper/2107.04034/) (2021)
- [Learning agile and dynamic motor skills for legged robots](https://mlsanity.com/paper/1901.08652/) (2019)
- [Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robots](https://mlsanity.com/paper/2103.14295/) (2021)
- [Sim-to-Real Learning of All Common Bipedal Gaits via Periodic Reward Composition](https://mlsanity.com/paper/2011.01387/) (2020)
- [Blind Bipedal Stair Traversal via Sim-to-Real Reinforcement Learning](https://mlsanity.com/paper/2105.08328/) (2021)
- [Multi-expert learning of adaptive legged locomotion](https://mlsanity.com/paper/2012.05810/) (2020)
- [ALLSTEPS: Curriculum-driven Learning of Stepping Stone Skills](https://mlsanity.com/paper/2005.04323/) (2020)
- [Teleoperation of Humanoid Robots: A Survey](https://mlsanity.com/paper/2301.04317/) (2023)
- [DeepWalk: Omnidirectional Bipedal Gait by Deep Reinforcement Learning](https://mlsanity.com/paper/2106.00534/) (2021)
- [Learning Bipedal Walking for Humanoids with Current Feedback](https://mlsanity.com/paper/2303.03724/) (2023)
- [Robust Feedback Motion Policy Design Using Reinforcement Learning on a 3D Digit Bipedal Robot](https://mlsanity.com/paper/2103.15309/) (2021)
- [Learning Bipedal Walking On Planned Footsteps For Humanoid Robots](https://mlsanity.com/paper/2207.12644/) (2022)
- [Learning Dynamic Bipedal Walking Across Stepping Stones](https://mlsanity.com/paper/2205.01807/) (2022)
- [Learning Whole-body Motor Skills for Humanoids](https://mlsanity.com/paper/2002.02991/) (2020)
- [mc-mujoco: Simulating Articulated Robots with FSM Controllers in MuJoCo](https://mlsanity.com/paper/2209.00274/) (2022)

## Abstract (arXiv)

End-to-end reinforcement learning (RL) for humanoid locomotion is appealing for its compact perception-action mapping, yet practical policies often suffer from training instability, inefficient feature fusion, and high actuation cost. We present HuMam, a state-centric end-to-end RL framework that employs a single-layer Mamba encoder to fuse robot-centric states with oriented footstep targets and a continuous phase clock. The policy outputs joint position targets tracked by a low-level PD loop and is optimized with PPO. A concise six-term reward balances contact quality, swing smoothness, foot placement, posture, and body stability while implicitly promoting energy saving. On the JVRC-1 humanoid in mc-mujoco, HuMam consistently improves learning efficiency, training stability, and overall task performance over a strong feedforward baseline, while reducing power consumption and torque peaks. To our knowledge, this is the first end-to-end humanoid RL controller that adopts Mamba as the fusion backbone, demonstrating tangible gains in efficiency, stability, and control economy.