Glossary · Term

entropy bonus

← all terms

Definition

Plain language

A small training reward for keeping the model's options open and uncertain, rather than locking onto one choice too early.

As stated in the literature

A reinforcement-learning shaping term that rewards higher output entropy to encourage exploration; long treated as a hand-tuned folk-wisdom hack, but shown in rollout-informativeness work to fall out directly as a term in the greedy marginal gain of a submodular informativeness objective.

Why it matters: It keeps a learning system exploring options long enough to find good strategies, rather than prematurely locking onto a mediocre one.

For example, the training nudges a model to keep considering several plausible next moves instead of fixating on the first one it happens to favor.

Heard on the show

“The regularizers — the KL divergence penalty pulling you toward a reference model, the entropy bonus keeping you from collapsing — are computed without reference to reward at all.”
Episode 010 — When Reward Climbs But Reasoning Goes Generic: Diagnosing Template Collapse in Agentic RL

Mentioned in 2 episodes

  1. 162
    The Empty-Lake Proof: Why More Rollouts Stop Helping Reasoning Models
  2. 010
    When Reward Climbs But Reasoning Goes Generic: Diagnosing Template Collapse in Agentic RL

Related terms