# Discovering Adaptable Symbolic Algorithms from Scratch

arXiv: https://arxiv.org/abs/2307.16890 · HTML: https://mlsanity.com/paper/2307.16890/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 42 references that are in the map.
- First posted on arXiv 31 Jul 2023.

## Builds on (most cited first, 15 of 15)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [Regularized Evolution for Image Classifier Architecture Search](https://mlsanity.com/paper/1802.01548/) (2018)
- [RMA: Rapid Motor Adaptation for Legged Robots](https://mlsanity.com/paper/2107.04034/) (2021)
- [Robots that can adapt like animals](https://mlsanity.com/paper/1407.3501/) (2014)
- [AutoML-Zero: Evolving Machine Learning Algorithms From Scratch](https://mlsanity.com/paper/2003.03384/) (2020)
- [Preparing for the Unknown: Learning a Universal Policy with Online System Identification](https://mlsanity.com/paper/1702.02453/) (2017)
- [ES-MAML: Simple Hessian-Free Meta Learning](https://mlsanity.com/paper/1910.01215/) (2019)
- [Learning Fast Adaptation with Meta Strategy Optimization](https://mlsanity.com/paper/1909.12995/) (2019)
- [Sub-policy Adaptation for Hierarchical Reinforcement Learning](https://mlsanity.com/paper/1906.05862/) (2019)
- [Meta-Learning through Hebbian Plasticity in Random Networks](https://mlsanity.com/paper/2007.02686/) (2020)
- [Meta-learning in natural and artificial intelligence](https://mlsanity.com/paper/2011.13464/) (2020)
- [TensorFlow Agents: Efficient Batched Reinforcement Learning in TensorFlow](https://mlsanity.com/paper/1709.02878/) (2017)
- [Unified Functional Hashing in Automatic Machine Learning](https://mlsanity.com/paper/2302.05433/) (2023)

## Built on by (most cited first, 4 of 4)

- [AutoNumerics-Zero: Automated Discovery of State-of-the-Art Mathematical Functions](https://mlsanity.com/paper/2312.08472/) (2023)
- [Neuron-centric Hebbian Learning](https://mlsanity.com/paper/2403.12076/) (2024)
- [Discovering Continuous-Time Memory-Based Symbolic Policies using Genetic Programming](https://mlsanity.com/paper/2406.02765/) (2024)
- [Real-time Learning and Evolution in Robotic Art Installations](https://mlsanity.com/paper/2609.13352/) (2026)

## Abstract (arXiv)

Autonomous robots deployed in the real world will need control policies that rapidly adapt to environmental changes. To this end, we propose AutoRobotics-Zero (ARZ), a method based on AutoML-Zero that discovers zero-shot adaptable policies from scratch. In contrast to neural network adaptation policies, where only model parameters are optimized, ARZ can build control algorithms with the full expressive power of a linear register machine. We evolve modular policies that tune their model parameters and alter their inference algorithm on-the-fly to adapt to sudden environmental changes. We demonstrate our method on a realistic simulated quadruped robot, for which we evolve safe control policies that avoid falling when individual limbs suddenly break. This is a challenging task in which two popular neural network baselines fail. Finally, we conduct a detailed analysis of our method on a novel and challenging non-stationary control task dubbed Cataclysmic Cartpole. Results confirm our findings that ARZ is significantly more robust to sudden environmental changes and can build simple, interpretable control policies.