Inducing Functions through Reinforcement Learning without Task Specification
arXiv:2111.11647
Abstract
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.
arXiv comment14 pages
References in corpus (8)
- Semi-Supervised Learning with Deep Generative Models
- Recurrent World Models Facilitate Policy Evolution
- Adversarial Autoencoders
- Agent57: Outperforming the Atari Human Benchmark
- Memory-based control with recurrent neural networks
- Never Give Up: Learning Directed Exploration Strategies
- A Conceptual Bio-Inspired Framework for the Evolution of Artificial General Intelligence
- Mimicking Evolution with Reinforcement Learning