Jump-Start Reinforcement Learning with Self-Evolving Priors for Extreme Monopedal Locomotion

2025-07-01 · Ziang Zheng, Guojian Zhan, Shiqi Liu, Yao Lyu, Tao Zhang, Shengbo Eben Li arxiv

Reinforcement learning (RL) has shown great potential in enabling quadruped robots to perform agile locomotion. However, directly training policies to simultaneously handle dual extreme challenges, i.e., extreme underactuation and extreme terrains, as in monopedal hopping tasks, remains highly challenging due to unstable early-stage interactions and unreliable reward feedback. To address this, we propose JumpER (jump-start reinforcement learning via self-evolving priors), an RL training framework that structures policy learning into multiple stages of increasing complexity. By dynamically generating self-evolving priors through iterative bootstrapping of previously learned policies, JumpER progressively refines and enhances guidance, thereby stabilizing exploration and policy optimization without relying on external expert priors or handcrafted reward shaping. Specifically, when integrated with a structured three-stage curriculum that incrementally evolves action modality, observation space, and task objective, JumpER enables quadruped robots to achieve robust monopedal hopping on unpredictable terrains for the first time. Remarkably, the resulting policy effectively handles challenging scenarios that traditional methods struggle to conquer, including wide gaps up to 60 cm, irregularly spaced stairs, and stepping stones with distances varying from 15 cm to 35 cm. JumpER thus provides a principled and scalable approach for addressing locomotion tasks under the dual challenges of extreme underactuation and extreme terrains.

📄 PDF Abstract BibTeX arXiv:2507.01243

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Self-Evolving Scientific Agent Designs Physically Reasoned White-Box Fluid Control

2026-06-07 · Boai Sun, Wenjin Guo, Zongmin Yu, Liu Yang arxiv

While neural networks excel in autonomous control, their black-box nature makes control decisions difficult to interpret and diagnose in dynamic fluids. Here, we show how self-evolving scientific agents can design explic…

Reinforcement Learning Physical Simulations Code Generation

Value Function Initialization for Knowledge Transfer and Jump-start in Deep Reinforcement Learning

2025-08-12 · Soumia Mehimeh arxiv

Value function initialization (VFI) is an effective way to achieve a jumpstart in reinforcement learning (RL) by leveraging value estimates from prior tasks. While this approach is well established in tabular settings, e…

Reinforcement Learning Continuous Control

Rocket Landing Control with Random Annealing Jump Start Reinforcement Learning

2024-07-21 · YuXuan Jiang, Yujie Yang, Zhiqian Lan, Guojian Zhan 외

Rocket recycling is a crucial pursuit in aerospace technology, aimed at reducing costs and environmental impact in space exploration. The primary focus centers on rocket landing control, involving the guidance of a nonli…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Continuous Versatile Jumping Using Learned Action Residuals

2023-04-17 · Yuxiang Yang, Xiangyun Meng, Wenhao Yu, Tingnan Zhang 외

Jumping is essential for legged robots to traverse through difficult terrains. In this work, we propose a hierarchical framework that combines optimal control and reinforcement learning to learn continuous jumping motion…