Global progress in competitive co-evolution: a systematic comparison of alternative methods
The usage of broad sets of training data is paramount to evolve adaptive agents. In this respect, competitive co-evolution is a widespread technique in which the coexistence of different learning agents fosters adaptation, which in turn makes agents experience continuously varying environmental cond...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Robotics and AI |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/frobt.2024.1470886/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832592171179442176 |
|---|---|
| author | Stefano Nolfi Paolo Pagliuca |
| author_facet | Stefano Nolfi Paolo Pagliuca |
| author_sort | Stefano Nolfi |
| collection | DOAJ |
| description | The usage of broad sets of training data is paramount to evolve adaptive agents. In this respect, competitive co-evolution is a widespread technique in which the coexistence of different learning agents fosters adaptation, which in turn makes agents experience continuously varying environmental conditions. However, a major pitfall is related to the emergence of endless limit cycles where agents discover, forget and rediscover similar strategies during evolution. In this work, we investigate the use of competitive co-evolution for synthesizing progressively better solutions. Specifically, we introduce a set of methods to measure historical and global progress. We discuss the factors that facilitate genuine progress. Finally, we compare the efficacy of four qualitatively different algorithms, including two newly introduced methods. The selected algorithms promote genuine progress by creating an archive of opponents used to evaluate evolving individuals, generating archives that include high-performing and well-differentiated opponents, identifying and discarding variations that lead to local progress only (i.e., progress against the opponents experienced and retrogressing against others). The results obtained in a predator-prey scenario, commonly used to study competitive evolution, demonstrate that all the considered methods lead to global progress in the long term. However, the rate of progress and the ratio of progress versus retrogressions vary significantly among algorithms. In particular, our outcomes indicate that the Generalist method introduced in this work outperforms the other three considered methods and represents the only algorithm capable of producing global progress during evolution. |
| format | Article |
| id | doaj-art-bf94d9082306406890634933f3777f36 |
| institution | Kabale University |
| issn | 2296-9144 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Robotics and AI |
| spelling | doaj-art-bf94d9082306406890634933f3777f362025-01-21T13:21:41ZengFrontiers Media S.A.Frontiers in Robotics and AI2296-91442025-01-011110.3389/frobt.2024.14708861470886Global progress in competitive co-evolution: a systematic comparison of alternative methodsStefano NolfiPaolo PagliucaThe usage of broad sets of training data is paramount to evolve adaptive agents. In this respect, competitive co-evolution is a widespread technique in which the coexistence of different learning agents fosters adaptation, which in turn makes agents experience continuously varying environmental conditions. However, a major pitfall is related to the emergence of endless limit cycles where agents discover, forget and rediscover similar strategies during evolution. In this work, we investigate the use of competitive co-evolution for synthesizing progressively better solutions. Specifically, we introduce a set of methods to measure historical and global progress. We discuss the factors that facilitate genuine progress. Finally, we compare the efficacy of four qualitatively different algorithms, including two newly introduced methods. The selected algorithms promote genuine progress by creating an archive of opponents used to evaluate evolving individuals, generating archives that include high-performing and well-differentiated opponents, identifying and discarding variations that lead to local progress only (i.e., progress against the opponents experienced and retrogressing against others). The results obtained in a predator-prey scenario, commonly used to study competitive evolution, demonstrate that all the considered methods lead to global progress in the long term. However, the rate of progress and the ratio of progress versus retrogressions vary significantly among algorithms. In particular, our outcomes indicate that the Generalist method introduced in this work outperforms the other three considered methods and represents the only algorithm capable of producing global progress during evolution.https://www.frontiersin.org/articles/10.3389/frobt.2024.1470886/fullcompetitive co-evolutionevolutionary roboticslocal historical and global progressopen-ended evolutionpredator-prey robots |
| spellingShingle | Stefano Nolfi Paolo Pagliuca Global progress in competitive co-evolution: a systematic comparison of alternative methods Frontiers in Robotics and AI competitive co-evolution evolutionary robotics local historical and global progress open-ended evolution predator-prey robots |
| title | Global progress in competitive co-evolution: a systematic comparison of alternative methods |
| title_full | Global progress in competitive co-evolution: a systematic comparison of alternative methods |
| title_fullStr | Global progress in competitive co-evolution: a systematic comparison of alternative methods |
| title_full_unstemmed | Global progress in competitive co-evolution: a systematic comparison of alternative methods |
| title_short | Global progress in competitive co-evolution: a systematic comparison of alternative methods |
| title_sort | global progress in competitive co evolution a systematic comparison of alternative methods |
| topic | competitive co-evolution evolutionary robotics local historical and global progress open-ended evolution predator-prey robots |
| url | https://www.frontiersin.org/articles/10.3389/frobt.2024.1470886/full |
| work_keys_str_mv | AT stefanonolfi globalprogressincompetitivecoevolutionasystematiccomparisonofalternativemethods AT paolopagliuca globalprogressincompetitivecoevolutionasystematiccomparisonofalternativemethods |