# Reinforcement Learning Controllers for Soft Robots using Learned Environments

arXiv: https://arxiv.org/abs/2410.18519 · HTML: https://mlsanity.com/paper/2410.18519/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods.
- Builds on 6 of its 27 references that are in the map.
- First posted on arXiv 24 Oct 2024.

## 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, 6 of 6)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Robot Operating System 2: Design, Architecture, and Uses In The Wild](https://mlsanity.com/paper/2211.07752/) (2022)
- [Discovered Policy Optimisation](https://mlsanity.com/paper/2210.05639/) (2022)
- [Podracer architectures for scalable Reinforcement Learning](https://mlsanity.com/paper/2104.06272/) (2021)
- [Analyzing and Exploiting NARX Recurrent Neural Networks for Long-Term Dependencies](https://mlsanity.com/paper/1702.07805/) (2017)

## Built on by (most cited first, 3 of 3)

- [Hysteresis-Aware Neural Network Modeling and Whole-Body Reinforcement Learning Control of Soft Robots](https://mlsanity.com/paper/2504.13582/) (2025)
- [Contact-Aided Navigation of Flexible Robotic Endoscope Using Deep Reinforcement Learning in Dynamic Stomach](https://mlsanity.com/paper/2509.00319/) (2025)
- [DiSA-IQL: Offline Reinforcement Learning for Robust Soft Robot Control under Distribution Shifts](https://mlsanity.com/paper/2510.00358/) (2025)

## Abstract (arXiv)

Soft robotic manipulators offer operational advantage due to their compliant and deformable structures. However, their inherently nonlinear dynamics presents substantial challenges. Traditional analytical methods often depend on simplifying assumptions, while learning-based techniques can be computationally demanding and limit the control policies to existing data. This paper introduces a novel approach to soft robotic control, leveraging state-of-the-art policy gradient methods within parallelizable synthetic environments learned from data. We also propose a safety oriented actuation space exploration protocol via cascaded updates and weighted randomness. Specifically, our recurrent forward dynamics model is learned by generating a training dataset from a physically safe textitmean reverting random walk in actuation space to explore the partially-observed state-space. We demonstrate a reinforcement learning approach towards closed-loop control through state-of-the-art actor-critic methods, which efficiently learn high-performance behaviour over long horizons. This approach removes the need for any knowledge regarding the robot's operation or capabilities and sets the stage for a comprehensive benchmarking tool in soft robotics control.