# Inducing Functions through Reinforcement Learning without Task Specification

arXiv: https://arxiv.org/abs/2111.11647 · HTML: https://mlsanity.com/paper/2111.11647/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 29 references that are in the map.
- First posted on arXiv 23 Nov 2021.

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

- [Recurrent World Models Facilitate Policy Evolution](https://mlsanity.com/paper/1809.01999/) (2018)
- [A Distributional Perspective on Reinforcement Learning](https://mlsanity.com/paper/1707.06887/) (2017)
- [Model-Based Reinforcement Learning for Atari](https://mlsanity.com/paper/1903.00374/) (2019)
- [Semi-Supervised Learning with Deep Generative Models](https://mlsanity.com/paper/1406.5298/) (2014)
- [Deep Recurrent Q-Learning for Partially Observable MDPs](https://mlsanity.com/paper/1507.06527/) (2015)
- [Adversarial Autoencoders](https://mlsanity.com/paper/1511.05644/) (2015)
- [Agent57: Outperforming the Atari Human Benchmark](https://mlsanity.com/paper/2003.13350/) (2020)
- [Never Give Up: Learning Directed Exploration Strategies](https://mlsanity.com/paper/2002.06038/) (2020)
- [Memory-based control with recurrent neural networks](https://mlsanity.com/paper/1512.04455/) (2015)
- [Deep neuroethology of a virtual rodent](https://mlsanity.com/paper/1911.09451/) (2019)
- [Mimicking Evolution with Reinforcement Learning](https://mlsanity.com/paper/2004.00048/) (2020)

## Built on by (most cited first, 1 of 1)

- [Human-AI Shared Control via Policy Dissection](https://mlsanity.com/paper/2206.00152/) (2022)

## Abstract (arXiv)

We report a bio-inspired framework for training a neural network through reinforcement learning to induce high level functions within the network. Based on the interpretation that animals have gained their cognitive functions such as object recognition - without ever being specifically trained for - as a result of maximizing their fitness to the environment, we place our agent in an environment where developing certain functions may facilitate decision making. The experimental results show that high level functions, such as image classification and hidden variable estimation, can be naturally and simultaneously induced without any pre-training or specifying them.