Altruism in Fuzzy Reinforcement Learning
- 14 October 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 12 (1) , 348-361
Abstract
We propose using a genetic algorithm to select hyperparameters in multiagent reinforcement learning (MARL) settings. In particular, we look at this in the context of cooperation and altruism. We show through the use of three continuous space games, that certain algorithmic hyperparameters are better suited to allow to agents learn altruistic behaviors. The agents learn using fuzzy actor critic learning algorithms in either a hierarchical structure or a single actor critic policy. The genetic algorithm selects the discount factors, the reward weights, and the standard deviation of noise applied to actor during learning. The genetic algorithm uses a fitness function based on the ratio of successful tests the group of agents can pass after training. This automated selection of these specific hyperparameters show that they are important for cooperation and also not trivial to select.Keywords
This publication has 13 references indexed in Scilit:
- Privacy Preserving Demand Side Management Method via Multi-Agent Reinforcement LearningIEEE/CAA Journal of Automatica Sinica, 2023
- MUTS-Based Cooperative Target Stalking for A Multi-USV SystemIEEE/CAA Journal of Automatica Sinica, 2022
- Altruistic behaviors and cooperation among gifted adolescentsFrontiers in Psychology, 2022
- Deception in A Multi-agent Adversarial Game: The Game of Guarding Several Territories2020
- Fuzzy Reinforcement Learning for Robust Spectrum Access in Dynamic Shared NetworksIEEE Access, 2019
- A PSO-Optimized Fuzzy Reinforcement Learning Method for Making the Minimally Invasive Surgical Arm ClevererIEEE Access, 2019
- Deep Reinforcement Learning Using Genetic Algorithm for Parameter Optimization2019
- Speeding up the Hyperparameter Optimization of Deep Convolutional Neural NetworksInternational Journal of Computational Intelligence and Applications, 2018
- Ant Colony Optimization Incorporated With Fuzzy Q-Learning for Reinforcement Fuzzy ControlIEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans, 2009
- Social semantics: altruism, cooperation, mutualism, strong reciprocity and group selectionJournal of Evolutionary Biology, 2006