activity
20172022
most citedIndividual specialization in multi-task environments with multiagent reinforcement learners

1 citations · 2 across the 5 of their papers we have counts for

collaborators

6 papers

cs.MA2022

Cooperative control of environmental extremes by artificial intelligent agents

Martí Sánchez-Fibla, Clément Moulin-Frier, Ricard Solé

Humans have been able to tackle biosphere complexities by acting as ecosystem engineers, profoundly changing the flows of matter, energy and information. This includes major innova…

cs.AI20191 cited

Individual specialization in multi-task environments with multiagent reinforcement learners

Marco Jerome Gasparrini, Ricard Solé, Martí Sánchez-Fibla

There is a growing interest in Multi-Agent Reinforcement Learning (MARL) as the first steps towards building general intelligent agents that learn to make low and high-level decisi…

cs.AI2019

Loss aversion fosters coordination among independent reinforcement learners

Marco Jerome Gasparrini, Martí Sánchez-Fibla

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)…

cs.LG20191 cited

Speeding up reinforcement learning by combining attention and agency features

Berkay Demirel, Martí Sánchez-Fibla

When playing video-games we immediately detect which entity we control and we center the attention towards it to focus the learning and reduce its dimensionality. Reinforcement Lea…

cs.MA2018

Modeling the Formation of Social Conventions from Embodied Real-Time Interactions

Ismael T. Freire, Clement Moulin-Frier, Marti Sanchez-Fibla +2

What is the role of real-time control and learning in the formation of social conventions? To answer this question, we propose a computational model that matches human behavioral d…

cs.AI2017

A correlational analysis of multiagent sensorimotor interactions: clustering autonomous and controllable entities

M. Sánchez-Fibla, C. Moulin-Frier, X. Arsiwalla +1

A first step to reach Theory of Mind (ToM) abilities (attribution of beliefs to others) in synthetic agents through sensorimotor interactions, would be to tag sensory data with age…