DeepAI AI Chat
Log In Sign Up

Learning to solve arithmetic problems with a virtual abacus

by   Flavio Petruzzellis, et al.
Università di Padova

Acquiring mathematical skills is considered a key challenge for modern Artificial Intelligence systems. Inspired by the way humans discover numerical knowledge, here we introduce a deep reinforcement learning framework that allows to simulate how cognitive agents could gradually learn to solve arithmetic problems by interacting with a virtual abacus. The proposed model successfully learn to perform multi-digit additions and subtractions, achieving an error rate below 1 during training. We also compare the performance of learning agents receiving a different amount of explicit supervision, and we analyze the most common error patterns to better understand the limitations and biases resulting from our design choices.


page 1

page 2

page 3

page 4


Learning to Perform Physics Experiments via Deep Reinforcement Learning

When encountering novel objects, humans are able to infer a wide range o...

Deep Reinforcement Learning in a Monetary Model

We propose using deep reinforcement learning to solve dynamic stochastic...

Projective simulation for classical learning agents: a comprehensive investigation

We study the model of projective simulation (PS), a novel approach to ar...

Towards sample-efficient episodic control with DAC-ML

The sample-inefficiency problem in Artificial Intelligence refers to the...

Learning to Solve Complex Tasks by Talking to Agents

Humans often solve complex problems by interacting (in natural language)...