# Training in Task Space to Speed Up and Guide Reinforcement Learning

arXiv: https://arxiv.org/abs/1903.02219 · HTML: https://mlsanity.com/paper/1903.02219/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Mar 2019.

## Built on by (most cited first, 7 of 7)

- [CPG-RL: Learning Central Pattern Generators for Quadruped Locomotion](https://mlsanity.com/paper/2211.00458/) (2022)
- [Robust High-speed Running for Quadruped Robots via Deep Reinforcement Learning](https://mlsanity.com/paper/2103.06484/) (2021)
- [Visual CPG-RL: Learning Central Pattern Generators for Visually-Guided Quadruped Locomotion](https://mlsanity.com/paper/2212.14400/) (2022)
- [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)
- [Guided Reinforcement Learning for Omnidirectional 3D Jumping in Quadruped Robots](https://mlsanity.com/paper/2507.16481/) (2025)
- [Quadruped Locomotion on Non-Rigid Terrain using Reinforcement Learning](https://mlsanity.com/paper/2107.02955/) (2021)
- [Efficient Reinforcement Learning for Jumping Monopods](https://mlsanity.com/paper/2309.07038/) (2023)

## Abstract (arXiv)

Recent breakthroughs in the reinforcement learning (RL) community have made significant advances towards learning and deploying policies on real world robotic systems. However, even with the current state-of-the-art algorithms and computational resources, these algorithms are still plagued with high sample complexity, and thus long training times, especially for high degree of freedom (DOF) systems. There are also concerns arising from lack of perceived stability or robustness guarantees from emerging policies. This paper aims at mitigating these drawbacks by: (1) modeling a complex, high DOF system with a representative simple one, (2) making explicit use of forward and inverse kinematics without forcing the RL algorithm to "learn" them on its own, and (3) learning locomotion policies in Cartesian space instead of joint space. In this paper these methods are applied to JPL's Robosimian, but can be readily used on any system with a base and end effector(s). These locomotion policies can be produced in just a few minutes, trained on a single laptop. We compare the robustness of the resulting learned policies to those of other control methods. An accompanying video for this paper can be found at https://youtu.be/xDxxSw5ahnc .