# Learning Agile Locomotion Skills with a Mentor

arXiv: https://arxiv.org/abs/2011.05541 · HTML: https://mlsanity.com/paper/2011.05541/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Nov 2020.

## Built on by (most cited first, 8 of 8)

- [Adversarial Motion Priors Make Good Substitutes for Complex Reward Functions](https://mlsanity.com/paper/2203.15103/) (2022)
- [Learning to Jump from Pixels](https://mlsanity.com/paper/2110.15344/) (2021)
- [Barkour: Benchmarking Animal-level Agility with Quadruped Robots](https://mlsanity.com/paper/2305.14654/) (2023)
- [Learning and Adapting Agile Locomotion Skills by Transferring Experience](https://mlsanity.com/paper/2304.09834/) (2023)
- [PA-LOCO: Learning Perturbation-Adaptive Locomotion for Quadruped Robots](https://mlsanity.com/paper/2407.04224/) (2024)
- [Puppeteer and Marionette: Learning Anticipatory Quadrupedal Locomotion Based on Interactions of a Central Pattern Generator and Supraspinal Drive](https://mlsanity.com/paper/2302.13378/) (2023)
- [Expanding Versatility of Agile Locomotion through Policy Transitions Using Latent State Representation](https://mlsanity.com/paper/2306.08224/) (2023)
- [Hierarchical Reinforcement Learning and Value Optimization for Challenging Quadruped Locomotion](https://mlsanity.com/paper/2506.20036/) (2025)

## Abstract (arXiv)

Developing agile behaviors for legged robots remains a challenging problem. While deep reinforcement learning is a promising approach, learning truly agile behaviors typically requires tedious reward shaping and careful curriculum design. We formulate agile locomotion as a multi-stage learning problem in which a mentor guides the agent throughout the training. The mentor is optimized to place a checkpoint to guide the movement of the robot's center of mass while the student (i.e. the robot) learns to reach these checkpoints. Once the student can solve the task, we teach the student to perform the task without the mentor. We evaluate our proposed learning system with a simulated quadruped robot on a course consisting of randomly generated gaps and hurdles. Our method significantly outperforms a single-stage RL baseline without a mentor, and the quadruped robot can agilely run and jump across gaps and obstacles. Finally, we present a detailed analysis of the learned behaviors' feasibility and efficiency.