# Artificial Intelligence for Prosthetics - challenge solutions

arXiv: https://arxiv.org/abs/1902.02441 · HTML: https://mlsanity.com/paper/1902.02441/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Feb 2019.

## Built on by (most cited first, 12 of 12)

- [Learning to run a Power Network Challenge: a Retrospective Analysis](https://mlsanity.com/paper/2103.03104/) (2021)
- [DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systems](https://mlsanity.com/paper/2206.00484/) (2022)
- [Latent Exploration for Reinforcement Learning](https://mlsanity.com/paper/2305.20065/) (2023)
- [DynSyn: Dynamical Synergistic Representation for Efficient Learning and Control in Overactuated Embodied Systems](https://mlsanity.com/paper/2407.11472/) (2024)
- [Generative GaitNet](https://mlsanity.com/paper/2201.12044/) (2022)
- [KINESIS: Motion Imitation for Human Musculoskeletal Locomotion](https://mlsanity.com/paper/2503.14637/) (2025)
- [Learning with Muscles: Benefits for Data-Efficiency and Robustness in Anthropomorphic Tasks](https://mlsanity.com/paper/2207.03952/) (2022)
- [Bidirectional GaitNet: A Bidirectional Prediction Model of Human Gait and Anatomical Conditions](https://mlsanity.com/paper/2306.04161/) (2023)
- [Arnold: A multi-task, multi-embodiment muscle transformer policy](https://mlsanity.com/paper/2508.18066/) (2025)
- [Characterization of Human Balance through a Reinforcement Learning-based Muscle Controller](https://mlsanity.com/paper/2308.04462/) (2023)
- [Exciting Action: Investigating Efficient Exploration for Learning Musculoskeletal Humanoid Locomotion](https://mlsanity.com/paper/2407.11658/) (2024)
- [Real-Time Forecasting of Pathological Gait via IMU Navigation: A Few-Shot and Generative Learning Framework for Wearable Devices](https://mlsanity.com/paper/2405.09569/) (2024)

## Abstract (arXiv)

In the NeurIPS 2018 Artificial Intelligence for Prosthetics challenge, participants were tasked with building a controller for a musculoskeletal model with a goal of matching a given time-varying velocity vector. Top participants were invited to describe their algorithms. In this work, we describe the challenge and present thirteen solutions that used deep reinforcement learning approaches. Many solutions use similar relaxations and heuristics, such as reward shaping, frame skipping, discretization of the action space, symmetry, and policy blending. However, each team implemented different modifications of the known algorithms by, for example, dividing the task into subtasks, learning low-level control, or by incorporating expert knowledge and using imitation learning.