Reproducibility is a desirable property of scientific research. On the one hand, it increases confidence in results. On the other hand, reproducible results can be extended on a solid basis. In rapidly developing fields such as machine learning, the latter is particularly important to ensure the reliability of research. In this paper, we present a systematic approach to reproducing (using the available implementation), replicating (using an alternative implementation) and reevaluating (using different datasets) state-of-the-art experiments. This approach enables the early detection and correction of deficiencies and thus the development of more robust and transparent machine learning methods. We detail the independent reproduction, replication, and reevaluation of the initially published experiments with a method that we want to extend. For each step, we identify issues and draw lessons learned. We further discuss solutions that have proven effective in overcoming the encountered problems. This work can serve as a guide for further reproducibility studies and generally improve reproducibility in machine learning.

Reproduce, Replicate, Reevaluate. The Long but Safe Way to Extend Machine Learning Methods

Many artificial intelligence systems are developed which interact with human beings and other such systems, sometimes embodied as robots. Their behaviour is driven by the knowledge they have on their environment. This knowledge may be learnt from experience. This is actually what advertised machine learning systems do. However, such systems will only behave properly if this knowledge, or culture, is shared with others. This raises the question: can they socially evolve their knowledge as assumed in cultural evolution?
Answering this question calls for developments in computational cultural (knowledge) evolution. It is at a crossroad between two threads:
- Cultural knowledge evolution in which cultural evolution is applied to the knowledge and beliefs of organisms.
- Computational cultural evolution in which computer capabilities are used to synthetise and analyse cultural evolution. It may be both experimental in which short-term small experiments are performed, or observational, in which observations can be made in the long run on large populations.

Computational cultural knowledge evolution may actually cover two types of activities: Agent-based simulation of cultural evolution in which agents are a model that can predict how a modelled system works or Artificial cultural evolution in which programs or agents are new `organisms' exhibiting cultural evolution.
Both activities are worth pursuing to study the principles of cultural (knowledge) evolution. For instance, the discussion about other species failing to develop cumulative culture supports the conclusion that the human species has a unique feature: cumulativity. However, it may be more simply related to the capability to deal with complex cultural items which support cumulativity better or to rely on more elaborate adaptation mechanisms that provide this cumulativity. So far, it is not possible to decide. Similarly, it is difficult to provide direct evidence of the absence of replicator. Developing agents able to evolve cumulatively their culture could bring some insight in these debates.
We are experimenting with agents learning their knowledge from their environment and from other agents. They behave according to this knowledge and are able to adapt their knowledge in order to succeed in social games exploiting it. The advantage of using agents bearing an explicit representation of knowledge is that it is possible to assess the evolution of the properties of agents' knowledge. In particular, the accuracy, the consistency, or the diversity of the knowledge can be directly measured.

Can AI systems culturally evolve their knowledge?


Agents have been used for simulating cultural evolution and cultural evolution can be used as a model for artificial agents. Previous results have shown that horizontal, or intra-generation, knowledge transmission allows agents to improve the quality of their knowledge to a certain level. Moreover, variation generated through vertical, or inter-generation, transmission allows agents to exceed that level. Such results have been obtained under specific conditions such as the drastic selection of agents allowed to transmit their knowledge, seeding the process with correct knowledge or introducing artificial noise during transmission. Here, we question the necessity of such measures and study their impact on the quality of transmitted knowledge. For that purpose, we combine the settings of two previous experiments and we relax these assumptions (no strong selection of teachers, no fully correct seed, no introduction of artificial noise). The rationale is that if interactions lead agents to improve their overall knowledge quality, this should be sufficient to ensure correct knowledge transmission, and that transmission mechanisms are sufficiently imperfect to produce variation. In this setting, we confirm that vertical transmission improves on horizontal transmission even without drastic selection and oriented learning. We also show that horizontal transmission is able to compensate for the lack of parent selection if it is maintained for long enough. This shows that it is not necessary to take the most successful agents as teachers, neither in vertical nor horizontal transmission, to cumulatively improve knowledge.

Knowledge Transmission and Improvement Across Generations do not Need Strong Selection

When agents independently learn knowledge, such as ontologies, about their environment, it may be diverse, incorrect or incomplete. This knowledge heterogeneity could lead agents to disagree, thus hindering their cooperation. Existing approaches usually deal with this interaction problem by relating ontologies, without modifying them, or, on the contrary, by focusing on building common knowledge. Here, we consider agents adapting ontologies learned from the environment in order to agree with each other when cooperating. In this scenario, fundamental questions arise: Do they achieve successful interaction? Can this process improve knowledge correctness? Do all agents end up with the same ontology? To answer these questions, we design a two-stage experiment. First, agents learn to take decisions about the environment by classifying objects and the learned classifiers are turned into ontologies. In the second stage, agents interact with each other to agree on the decisions to take and modify their ontologies accordingly. We show that agents indeed reduce interaction failure, most of the time they improve the accuracy of their knowledge about the environment, and they do not necessarily opt for the same ontology.

Knowledge Improvement and Diversity under Interaction-Driven Adaptation of Learned Ontologies

Ontology alignments enable agents to communicate while preserving heterogeneity in their information. Alignments may not be provided as input and should be able to evolve when communication fails or when new information contradicting the alignment is acquired. In the Alignment Repair Game (ARG) this evolution is achieved via adaptation operators. ARG was evaluated experimentally and the experiments showed that agents converge towards successful communication and improve their alignments. However, whether the adaptation operators are formally correct, complete or redundant is still an open question. In this presentation, we introduce a formal framework based on Dynamic Epistemic Logic that allows us to answer this question. This framework allows us (1) to express the ontologies and alignments used, (2) to model the ARG adaptation operators through announcements and conservative upgrades and (3) to formally establish the correctness, partial redundancy and incompleteness of the adaptation operators in ARG.


Agent Ontology Alignment Repair through Dynamic Epistemic Logic

Main Track - Machine Learning

technical paper

We are pleased to announce the Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI-24), which will be held in Vancouver, British Columbia at the Vancouver Convention Centre – West Building from 20-27 February, 2024.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-24 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.

We expect for AAAI-24 to be an in-person conference – one author of all accepted papers will be expected to present work in person unless there are exceptional circumstances that prevent this.

In order to access the AAAI-24 event page you need to register [here](https://aaai.org/aaai-conference/registration/)

AAAI 2024

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. 

Please click on the button above to watch the recording of the live session.

Cultural evolutionary theory: Innovations, syntheses, and (hi)stories 1

### Welcome to the fourth Cultural Evolution Society Conference, CES2022! 

As last year, Underline will support the online component of the conference. The ongoing COVID-19 pandemic is causing a great deal of uncertainty for all of us. Therefore, we seek to offer a hybrid format that will hopefully allow some folks to travel to Aarhus, others to meet up locally or regionally in CES hub-lets, and other yet to participate online. The field of cultural evolution is growing in size and scope; its theories, methods and applications - both academic and applied - are getting ever more robust. Do join us in what promises to be an exciting exchange of ideas and a celebration of our field.

##### ***For SoMe interaction and live tweeting please tag @CulturalEvolSoc and use #CESconf2022***


#### The CES 2022 local organising committee
* Luseadra Joy McKerracher
* Jesper Sørensen 
* Niels Nørkjær Johannsen 
* Benjamin Grant Purzycki 
* Mette Løvschal 
* Felix Riede
* Iza Romanowska 
* Karsten Olsen

Please click on the button bellow if you want to watch the videos

Cultural Evolution Society 2022

The field of cultural evolution is growing in size and scope; its theories, methods and applications - both academic and applied - are getting ever more robust. Do join us in what promises to be an exciting exchange of ideas and a celebration of our field.

**Session Chair:** Nirav Ajmeri

Oral Session 1A4-3

AAMAS (International Conference on Autonomous Agents and Multiagent Systems) is the largest and most influential conference in the area of agents and multiagent systems. The aim of the conference is to bring together researchers and practitioners in all areas of agent technology and to provide a single, high-profile, internationally renowned forum for research in the theory and practice of autonomous agents and multiagent systems. AAMAS is the flagship conference of the non-profit International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS).

The AAMAS conference series was initiated in 2002 in Bologna, Italy as a joint event comprising the 6th International Conference on Autonomous Agents (AA), the 5th International Conference on Multiagent Systems (ICMAS), and the 9th International Workshop on Agent Theories, Architectures, and Languages (ATAL).

Subsequent AAMAS conferences have been held in Melbourne, Australia (July 2003), New York City, NY, USA (July 2004), Utrecht, The Netherlands (July 2005), Hakodate, Japan (May 2006), Honolulu, Hawaii, USA (May 2007), Estoril, Portugal (May 2008), Budapest, Hungary (May 2009), Toronto, Canada (May 2010), Taipei, Taiwan (May 2011), Valencia, Spain (June 2012), Minnesota, USA (May 2013), Paris, France (May 2014), Istanbul, Turkey (May 2015), Singapore (May 2016), São Paulo (2017) and Stockholm, Sweden (2018), Montreal (May 2019), Auckland (May 2020, Virtual), London (May 2021, Virtual).

A ticket is required to attend this event, please register using the link below:

https://aamas2022-conference.auckland.ac.nz/attending/registration/

Registration Is Required

AAMAS 2022

AAMAS (International Conference on Autonomous Agents and Multiagent Systems) is the largest and most influential conference in the area of agents and multiagent systems. The aim of the conference is to bring together researchers and practitioners in all areas of agent technology and to provide a single, high-profile, internationally renowned forum for research in the theory and practice of autonomous agents and multiagent systems. AAMAS is the flagship conference of the non-profit International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS).

S5: Multiagent Learning 3

AAMAS is the largest and most influential conference in the area of agents and multiagent systems, bringing together researchers and practitioners in all areas of agent technology and providing and internationally renowned high-profile forum for publishing and finding out about the latest developments in the field. AAMAS is the flagship conference of the non-profit International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS).  

![](https://assets.underline.io/uploads/markdown_image/1/image/ce4604bd54468a006164d16e080204fb.jpg)

Please click on the button below to register for this event.

If you are registered and see this page please check the account email you are logged in with. It must be the same as for the registration.

If you still have trouble accessing the contact please contact support at aamas2021@underline.io 

AAMAS 2021

Knowledge Representation, Reasoning and Planning

AAMAS is the leading scientific conference for research in autonomous agents and multi-agent systems. The AAMAS conference series was initiated in 2002 as the merging of three respected scientific meetings: the International Conference on Multi-Agent Systems (ICMAS), the International Workshop on Agent Theories, Architectures, and Languages (ATAL), and the International Conference on Autonomous Agents (AA). The aim of the joint conference is to provide a single, high-profile, internationally-respected archival forum for scientific research in the theory and practice of autonomous agents and multi-agent systems.

Browse keynotes, discussions, panels and over 300 presentations.


AAMAS 2020

AAMAS is the leading scientific conference for research in autonomous agents and multi-agent systems. The AAMAS conference series was initiated in 2002 as the merging of three respected scientific meetings: the International Conference on Multi-Agent Systems (ICMAS), the International Workshop on Agent Theories, Architectures, and Languages (ATAL), and the International Conference on Autonomous Agents (AA). 

Jérôme Euzenat

6

14

SHORT BIO

OTHER AFFILIATIONS

Presentations

Reproduce, Replicate, Reevaluate. The Long but Safe Way to Extend Machine Learning Methods

Can AI systems culturally evolve their knowledge?

Knowledge Transmission and Improvement Across Generations do not Need Strong Selection

Knowledge Improvement and Diversity under Interaction-Driven Adaptation of Learned Ontologies

Agent Ontology Alignment Repair through Dynamic Epistemic Logic

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES