DSLE: A Learning Environment for Dark Souls Boss Encounters
2026-08-10 • Artificial Intelligence
Artificial IntelligenceNeural and Evolutionary Computing
AI summaryⓘ
The authors created the Dark Souls Learning Environment (DSLE), which turns tough boss fights from the video game Dark Souls into challenges for AI agents to learn how to play. They picked a smaller set called DSLE-5 with five different types of fights to test different AI methods. While simple expert and evolutionary methods sometimes beat the first easy boss, more advanced AI like PPO and DQN struggle even after many hours of training. Overall, most bosses remain unconquered, showing how hard this environment is for AI, with failures measured by how long agents survive or how much damage they do, not just wins.
Dark Soulsreinforcement learningGymnasiumPPODQNevolutionary algorithmssparse rewardsreal-time combathigh-dimensional inputgame-playing agents
Authors
Derin Gezgin, Jim O'Connor, Tanner Goodwin, Gary B. Parker
Abstract
We introduce the Dark Souls Learning Environment (DSLE), a containerized platform that presents all 22 boss encounters of Dark Souls: Remastered as game-playing agent benchmarks through a Gymnasium-style interface. DSLE combines real-time combat, high-dimensional visual input, and sparse terminal rewards, with each environment step being a real action executed against the running game. To support controlled comparison, we define DSLE-5, a representative five-boss subset, spanning a melee fight, a spatially constrained arena, an environmental-hazard fight, a multi-target fight, and a fast final-boss fight, that we recommend as the starting suite for agents built on DSLE. On DSLE-5 we evaluate a random policy, an expert system, an evolutionary baseline, and PPO and DQN agents trained from visual input. The expert system and the evolutionary baseline each defeat the Asylum Demon, the game's tutorial boss (63% and 43% peak win rates), but none of the five methods defeats the other four DSLE-5 bosses; PPO and DQN show no measurable learning (at most 0.33% win rate on the tutorial boss, 0% elsewhere) within a budget that already costs tens of wall-clock hours per run. A broader study running the evolutionary baseline across all 22 encounters under advantaged all level-50 stats yields wins on only a handful of additional early-game bosses and leaves the rest unwon. The failure cases range from sub-10-second deaths in cramped, multi-target encounters to minute-long stalemates that inflict almost no damage, and we report them through survival time and damage dealt rather than win rate alone.