# Reinforcement Learning for Robust Athletic Intelligence: Lessons from the 2nd 'AI Olympics with RealAIGym' Competition

arXiv: https://arxiv.org/abs/2503.15290 · HTML: https://mlsanity.com/paper/2503.15290/

## Key facts

- Cited by 2 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 13 of its 25 references that are in the map.
- First posted on arXiv 19 Mar 2025.

## 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, 13 of 13)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [RLBench: The Robot Learning Benchmark & Learning Environment](https://mlsanity.com/paper/1909.12271/) (2019)
- [Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes](https://mlsanity.com/paper/2408.03539/) (2024)
- [An Open Torque-Controlled Modular Robot Architecture for Legged Locomotion Research](https://mlsanity.com/paper/1910.00093/) (2019)
- [Average-reward model-free reinforcement learning: a systematic review and literature mapping](https://mlsanity.com/paper/2010.08920/) (2020)
- [Benchmarking Structured Policies and Policy Optimization for Real-World Dexterous Object Manipulation](https://mlsanity.com/paper/2105.02087/) (2021)
- [Model-Based Policy Search Using Monte Carlo Gradient Estimation with Real Systems Application](https://mlsanity.com/paper/2101.12115/) (2021)
- [AcroMonk: A Minimalist Underactuated Brachiating Robot](https://mlsanity.com/paper/2305.08373/) (2023)
- [Maximum Entropy On-Policy Actor-Critic via Entropy Advantage Estimation](https://mlsanity.com/paper/2407.18143/) (2024)
- [RicMonk: A Three-Link Brachiation Robot with Passive Grippers for Energy-Efficient Brachiation](https://mlsanity.com/paper/2403.15762/) (2024)
- [AI Olympics challenge with Evolutionary Soft Actor Critic](https://mlsanity.com/paper/2409.01104/) (2024)

## Built on by (most cited first, 2 of 2)

- [Learning global control of underactuated systems with Model-Based Reinforcement Learning](https://mlsanity.com/paper/2504.06721/) (2025)
- [Average-Reward Maximum Entropy Reinforcement Learning for Global Policy in Double Pendulum Tasks](https://mlsanity.com/paper/2505.07516/) (2025)

## Abstract (arXiv)

In the field of robotics many different approaches ranging from classical planning over optimal control to reinforcement learning (RL) are developed and borrowed from other fields to achieve reliable control in diverse tasks. In order to get a clear understanding of their individual strengths and weaknesses and their applicability in real world robotic scenarios is it important to benchmark and compare their performances not only in a simulation but also on real hardware. The '2nd AI Olympics with RealAIGym' competition was held at the IROS 2024 conference to contribute to this cause and evaluate different controllers according to their ability to solve a dynamic control problem on an underactuated double pendulum system with chaotic dynamics. This paper describes the four different RL methods submitted by the participating teams, presents their performance in the swing-up task on a real double pendulum, measured against various criteria, and discusses their transferability from simulation to real hardware and their robustness to external disturbances.