Inducing Functions through Reinforcement Learning without Task Specification
Not on the map. Why?
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 11 of its 29 references that are in the map. First posted on arXiv 23 Nov 2021.
Builds on
11 of 29 references.
References · 11
- 2018Recurrent World Models Facilitate Policy Evolutioncited by 761
- 2017A Distributional Perspective on Reinforcement Learningcited by 743
- 2019Model-Based Reinforcement Learning for Ataricited by 495
- 2014Semi-Supervised Learning with Deep Generative Modelscited by 494
- 2015Deep Recurrent Q-Learning for Partially Observable MDPscited by 457
- 2015Adversarial Autoencoderscited by 359
- 2020Agent57: Outperforming the Atari Human Benchmarkcited by 300
- 2020Never Give Up: Learning Directed Exploration Strategiescited by 210
- 2015Memory-based control with recurrent neural networkscited by 77
- 2019Deep neuroethology of a virtual rodentcited by 22
- 2020Mimicking Evolution with Reinforcement Learningcited by 2
Built on by
Citing papers per year: 2022: 1.
1 paper.
- 2022Human-AI Shared Control via Policy Dissectioncited by 4
- 2022Human-AI Shared Control via Policy Dissection31 May 2022