Happiness Pursuit: Personality Learning in a Society of Agents

11/29/2017
by   Rafał Muszyński, et al.
0

Modeling personality is a challenging problem with applications spanning computer games, virtual assistants, online shopping and education. Many techniques have been tried, ranging from neural networks to computational cognitive architectures. However, most approaches rely on examples with hand-crafted features and scenarios. Here, we approach learning a personality by training agents using a Deep Q-Network (DQN) model on rewards based on psychoanalysis, against hand-coded AI in the game of Pong. As a result, we obtain 4 agents, each with its own personality. Then, we define happiness of an agent, which can be seen as a measure of alignment with agent's objective function, and study it when agents play both against hand-coded AI, and against each other. We find that the agents that achieve higher happiness during testing against hand-coded AI, have lower happiness when competing against each other. This suggests that higher happiness in testing is a sign of overfitting in learning to interact with hand-coded AI, and leads to worse performance against agents with different personalities.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/30/2019

Collaboration of AI Agents via Cooperative Multi-Agent Deep Reinforcement Learning

There are many AI tasks involving multiple interacting agents where agen...
research
07/12/2017

Learning Macromanagement in StarCraft from Replays using Deep Learning

The real-time strategy game StarCraft has proven to be a challenging env...
research
09/09/2018

A Continuous Information Gain Measure to Find the Most Discriminatory Problems for AI Benchmarking

This paper introduces an information-theoretic method for selecting a sm...
research
04/14/2021

GridToPix: Training Embodied Agents with Minimal Supervision

While deep reinforcement learning (RL) promises freedom from hand-labele...
research
04/28/2020

Evaluating the Rainbow DQN Agent in Hanabi with Unseen Partners

Hanabi is a cooperative game that challenges exist-ing AI techniques due...
research
06/18/2020

A Study on AI-FML Robotic Agent for Student Learning Behavior Ontology Construction

In this paper, we propose an AI-FML robotic agent for student learning b...
research
06/09/2023

Learning Not to Spoof

As intelligent trading agents based on reinforcement learning (RL) gain ...

Please sign up or login with your details

Forgot password? Click here to reset