| Autor: |
Wolfram Barfuss, Janusz M. Meylahn |
| Jazyk: |
angličtina |
| Rok vydání: |
2023 |
| Předmět: |
|
| Zdroj: |
Scientific Reports, Vol 13, Iss 1, Pp 1-13 (2023) |
| Druh dokumentu: |
article |
| ISSN: |
2045-2322 |
| DOI: |
10.1038/s41598-023-27672-7 |
| Popis: |
Abstract In this work, we ask for and answer what makes classical temporal-difference reinforcement learning with $$\epsilon$$ ϵ -greedy strategies cooperative. Cooperating in social dilemma situations is vital for animals, humans, and machines. While evolutionary theory revealed a range of mechanisms promoting cooperation, the conditions under which agents learn to cooperate are contested. Here, we demonstrate which and how individual elements of the multi-agent learning setting lead to cooperation. We use the iterated Prisoner’s dilemma with one-period memory as a testbed. Each of the two learning agents learns a strategy that conditions the following action choices on both agents’ action choices of the last round. We find that next to a high caring for future rewards, a low exploration rate, and a small learning rate, it is primarily intrinsic stochastic fluctuations of the reinforcement learning process which double the final rate of cooperation to up to 80%. Thus, inherent noise is not a necessary evil of the iterative learning process. It is a critical asset for the learning of cooperation. However, we also point out the trade-off between a high likelihood of cooperative behavior and achieving this in a reasonable amount of time. Our findings are relevant for purposefully designing cooperative algorithms and regulating undesired collusive effects. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
|
Nepřihlášeným uživatelům se plný text nezobrazuje |
K zobrazení výsledku je třeba se přihlásit.
|
