# Life, uh, Finds a Way: Hyperadaptability by Behavioral Search

arXiv: https://arxiv.org/abs/2410.01349 · HTML: https://mlsanity.com/paper/2410.01349/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 37 references that are in the map.
- First posted on arXiv 2 Oct 2024.

## Builds on (most cited first, 11 of 11)

- [Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model](https://mlsanity.com/paper/1911.08265/) (2019)
- [Unifying Count-Based Exploration and Intrinsic Motivation](https://mlsanity.com/paper/1606.01868/) (2016)
- [Reward-Free Exploration for Reinforcement Learning](https://mlsanity.com/paper/2002.02794/) (2020)
- [Using Fast Weights to Attend to the Recent Past](https://mlsanity.com/paper/1610.06258/) (2016)
- [Model-Free Episodic Control](https://mlsanity.com/paper/1606.04460/) (2016)
- [Reset-Free Reinforcement Learning via Multi-Task Learning: Learning Dexterous Manipulation Behaviors without Human Intervention](https://mlsanity.com/paper/2104.11203/) (2021)
- [Learning and Planning in Complex Action Spaces](https://mlsanity.com/paper/2104.06303/) (2021)
- [Learning Associative Inference Using Fast Weight Memory](https://mlsanity.com/paper/2011.07831/) (2020)
- [Count-Based Exploration in Feature Space for Reinforcement Learning](https://mlsanity.com/paper/1706.08090/) (2017)
- [You Only Live Once: Single-Life Reinforcement Learning](https://mlsanity.com/paper/2210.08863/) (2022)
- [Zipfian environments for Reinforcement Learning](https://mlsanity.com/paper/2203.08222/) (2022)

## Abstract (arXiv)

Living beings are able to solve a wide variety of problems that they encounter rarely or only once. Without the benefit of extensive and repeated experience with these problems, they can solve them in an ad-hoc manner. We call this capacity to always find a solution to a physically solvable problem hyperadaptability. To explain how hyperadaptability can be achieved, we propose a theory that frames behavior as the physical manifestation of a self-modifying search procedure. Rather than exploring randomly, our system achieves robust problem-solving by dynamically ordering an infinite set of continuous behaviors according to simplicity and effectiveness. Behaviors are sampled from paths over cognitive graphs, their order determined by a tight behavior-execution/graph-modification feedback loop. We implement cognitive graphs using Hebbian-learning and a novel harmonic neural representation supporting flexible information storage. We validate our approach through simulation experiments showing rapid achievement of highly-robust navigation ability in complex mazes, as well as high reward on difficult extensions of classic reinforcement learning problems. This framework offers a new theoretical model for developmental learning and paves the way for robots that can autonomously master complex skills and handle exceptional circumstances.