Theory of Mind with Guilt Aversion Facilitates Cooperative Reinforcement Learning

09/16/2020
by   Dung Nguyen, et al.
5

Guilt aversion induces experience of a utility loss in people if they believe they have disappointed others, and this promotes cooperative behaviour in human. In psychological game theory, guilt aversion necessitates modelling of agents that have theory about what other agents think, also known as Theory of Mind (ToM). We aim to build a new kind of affective reinforcement learning agents, called Theory of Mind Agents with Guilt Aversion (ToMAGA), which are equipped with an ability to think about the wellbeing of others instead of just self-interest. To validate the agent design, we use a general-sum game known as Stag Hunt as a test bed. As standard reinforcement learning agents could learn suboptimal policies in social dilemmas like Stag Hunt, we propose to use belief-based guilt aversion as a reward shaping mechanism. We show that our belief-based guilt averse agents can efficiently learn cooperative behaviours in Stag Hunt Games.

READ FULL TEXT

page 10

page 12

research
01/22/2021

Theory of Mind for Deep Reinforcement Learning in Hanabi

The partially observable card game Hanabi has recently been proposed as ...
research
07/30/2020

Improving Multi-Agent Cooperation using Theory of Mind

Recent advances in Artificial Intelligence have produced agents that can...
research
12/29/2019

Loss aversion fosters coordination among independent reinforcement learners

We study what are the factors that can accelerate the emergence of colla...
research
07/28/2017

A Survey of Learning in Multiagent Environments: Dealing with Non-Stationarity

The key challenge in multiagent learning is learning a best response to ...
research
03/02/2019

Efficient Reinforcement Learning with a Mind-Game for Full-Length StarCraft II

StarCraft II provides an extremely challenging platform for reinforcemen...
research
09/30/2022

Combining Theory of Mind and Abduction for Cooperation under Imperfect Information

In this paper, we formalise and implement an agent model for cooperation...
research
11/28/2019

Policies for constraining the behaviour of coalitions of agents in the context of algebraic information theory

This article takes an oblique sidestep from two previous papers, wherein...

Please sign up or login with your details

Forgot password? Click here to reset