Alternative names (2)
ruleChange • ruleModificationRandom triples
| Subject | Object |
|---|---|
| gptkb:Exponentially_Weighted_Recursive_Least_Squares | recursive |
| gptkb:Para_7-a-side_National_Team | no offside rule |
| gptkb:Least_Mean_Squares_algorithm | w(n+1) = w(n) + 2μe(n)x(n) |
| gptkb:WCST | rules change without warning |
| gptkb:Heavy_ball_method | x_{k+1} = x_k - \alpha \nabla f(x_k) + \beta (x_k - x_{k-1}) |
| gptkb:Three-check | game is won by giving three checks |
| gptkb:CPISRA_Football_7-a-side_World_Championships | shorter match duration |
| gptkb:Global_Rapid_Rugby | no kicking out on the full |
| gptkb:Dead-ball_era | ban on spitball in 1920 |
| gptkb:binary_PSO | probabilistic bit flipping |
| gptkb:Trust_Region_Policy_Optimization | constrained optimization |
| gptkb:Global_Rapid_Rugby | faster restarts |
| gptkb:Stochastic_gradient_descent | parameter update using single or few samples |
| gptkb:Policy_Gradient | Gradient Ascent |
| gptkb:Particle_Swarm_Optimization | velocity update |
| gptkb:State-Action-Reward-State-Action | Q(s,a) ← Q(s,a) + α [r + γ Q(s',a') - Q(s,a)] |
| gptkb:Ross_Chastain's_wall_ride_maneuver | NASCAR banned similar moves for future races |
| gptkb:NaSch_model | vehicle movement |
| gptkb:Para_7-a-side_National_Team | throw-ins can be one-handed |
| gptkb:RMSProp | divides learning rate by moving average of squared gradients |