Loss aversion fosters coordination among independent reinforcement learners

12/29/2019
by   Marco Jerome Gasparrini, et al.
0

We study what are the factors that can accelerate the emergence of collaborative behaviours among independent selfish learning agents. We depart from the "Battle of the Exes" (BoE), a spatial repeated game from which human behavioral data has been obtained (by Hawkings and Goldstone, 2016) that we find interesting because it considers two cases: a classic game theory version, called ballistic, in which agents can only make one action/decision (equivalent to the Battle of the Sexes) and a spatial version, called dynamic, in which agents can change decision (a spatial continuous version). We model both versions of the game with independent reinforcement learning agents and we manipulate the reward function transforming it into an utility introducing "loss aversion": the reward that an agent obtains can be perceived as less valuable when compared to what the other got. We prove experimentally the introduction of loss aversion fosters cooperation by accelerating its appearance, and by making it possible in some cases like in the dynamic condition. We suggest that this may be an important factor explaining the rapid converge of human behaviour towards collaboration reported in the experiment of Hawkings and Goldstone.

READ FULL TEXT
research
09/16/2020

Theory of Mind with Guilt Aversion Facilitates Cooperative Reinforcement Learning

Guilt aversion induces experience of a utility loss in people if they be...
research
02/16/2018

Learning multiagent coordination in the absence of communication channels

In this work, we develop a reinforcement learning protocol for a multiag...
research
07/30/2020

Moody Learners – Explaining Competitive Behaviour of Reinforcement Learning Agents

Designing the decision-making processes of artificial agents that are in...
research
04/10/2017

Dynamic Safe Interruptibility for Decentralized Multi-Agent Reinforcement Learning

In reinforcement learning, agents learn by performing actions and observ...
research
06/09/2020

Online Learning in Iterated Prisoner's Dilemma to Mimic Human Behavior

Prisoner's Dilemma mainly treat the choice to cooperate or defect as an ...
research
10/23/2022

A Cooperative Reinforcement Learning Environment for Detecting and Penalizing Betrayal

In this paper we present a Reinforcement Learning environment that lever...
research
06/14/2021

Targeted Data Acquisition for Evolving Negotiation Agents

Successful negotiators must learn how to balance optimizing for self-int...

Please sign up or login with your details

Forgot password? Click here to reset