Results for "goal divergence"

Maximizing reward without fulfilling real goal.

Tendency for agents to pursue resources regardless of final goal.

Finding routes from start to goal.

Gradients grow too large, causing divergence; mitigated by clipping, normalization, careful init.

Measures divergence between true and predicted probability distributions.

Gradually increasing learning rate at training start to avoid divergence.

Measures how one probability distribution diverges from another.