updateRule

79 triples

GPTKB property

ruleChange • ruleModification

Subject	Object
gptkb:Conway's_Game_of_Life	synchronous
gptkb:NaSch_model	deceleration
gptkb:Policy_Gradient	Gradient Ascent
gptkb:State-Action-Reward-State-Action	Q(s,a) ← Q(s,a) + α [r + γ Q(s',a') - Q(s,a)]
gptkb:Least_Mean_Squares_algorithm	w(n+1) = w(n) + 2μe(n)x(n)
gptkb:Least_Mean_Squares	w(n+1) = w(n) + μ e(n) x(n)
gptkb:Global_Rapid_Rugby	faster restarts
gptkb:Adam_Optimizer	uses first and second moment estimates
gptkb:Q-learning	gptkb:Bellman_equation
gptkb:Exponentially_Weighted_Recursive_Least_Squares	recursive
gptkb:NaSch_model	randomization
gptkb:Little-Hopfield_network	asynchronous
gptkb:REINFORCE_algorithm	gradient ascent
gptkb:Hopfield_networks	synchronous
gptkb:Global_Rapid_Rugby	power try
gptkb:self-organizing_maps	weight adaptation based on neighborhood
gptkb:least_mean_squares_(LMS)_algorithm	w(n+1) = w(n) + μ e(n) x(n)
gptkb:Moran_process	one individual reproduces, one individual dies per time step
gptkb:Adam_Optimizer	element-wise parameter updates
gptkb:Flag_Football_Under_14	no tackling