A contextual-bandit RL agent, trained in a D&D combat simulator, generates encounters that lengthen fights, lower party HP, and keep win rates near 80%, though these outcomes are direct reward components rather than independent discoveries.
No player left behind: evolving dungeons and dragons combat to optimize difficulty and player contributions,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
NTRL: Encounter Generation via Reinforcement Learning for Dynamic Difficulty Adjustment in Dungeons and Dragons
A contextual-bandit RL agent, trained in a D&D combat simulator, generates encounters that lengthen fights, lower party HP, and keep win rates near 80%, though these outcomes are direct reward components rather than independent discoveries.