notesum.ai

Published at October 23

Bridging Swarm Intelligence and Reinforcement Learning

cs.CV

cs.AI

Released Date: October 23, 2024

Authors: Karthik Soma¹, Yann Bouteiller, Heiko Hamann², Giovanni Beltrame

Aff.: ¹Polytechnique Montreal, Montreal, Canada; ²University of Konstanz, Konstanz, Germany

Arxiv: https://arxiv.org/abs/2410.17517v1

Refer to caption

Hyperparameter	value
Arms ( $n$ )	10
Learning rate ( $\alpha$ )	$\{0.001,0.1\}$
Epochs ( $E$ )	100
Variance ( $\sigma^{2})$	1
Runs ( $R$ )	$\{1000000,1000\}$
Weight factor ( $\gamma$ )	0.01
Discretizing factor ( $\delta$ )	$\alpha$
final time ( $t_{f}$ )	$\alpha\times R$ = 100