Summary
Researchers introduce the Dark Souls Learning Environment (DSLE), a containerized platform exposing all 22 boss fights of Dark Souls: Remastered as Gymnasium-style benchmarks for game-playing agents. DSLE features real-time combat, high-dimensional visual input, and sparse terminal rewards, where each environment step corresponds to a real action executed in the running game. To enable controlled comparisons, the authors define DSLE-5, a representative five-boss subset covering melee combat, a spatially constrained arena, environmental hazards, multi-target fights, and a fast final boss. Evaluations on DSLE-5 included a random policy, an expert system, an evolutionary baseline, and PPO and DQN agents trained from visual input. The expert system and evolutionary baseline beat the tutorial boss (Asylum Demon) with peak win rates of 63% and 43% respectively, but none of the five methods defeated the other four bosses. PPO and DQN showed no measurable learning within budgets of tens of hours per run, reaching at most 0.33% win rate on the tutorial boss. A broader evolutionary run across all 22 encounters, with fully maxed stats, won only a few additional early-game bosses. The paper reports failures via survival time and damage dealt, including sub-10-second deaths and near-minute stalemates.
Overview
Research area: Machine Learning
Authors: Derin Gezgin, Jim O'Connor, Tanner Goodwin
Published: 2026-08-11
arXiv: 2508.03798
Summary
The Dark Souls Learning Environment (DSLE) is 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, the authors define DSLE-5, a representative five-boss subset spanning:
- A melee fight
- A spatially constrained arena
- An environmental-hazard fight
- A multi-target fight
- A fast final-boss fight
DSLE-5 is recommended as the starting suite for agents built on DSLE.
Evaluation Results
On DSLE-5, the authors evaluated a random policy, an expert system, an evolutionary baseline, and PPO and DQN agents trained from visual input.
- Expert system: defeated the tutorial boss (Asylum Demon) with a peak win rate of 63%
- Evolutionary baseline: defeated Asylum Demon with a peak win rate of 43%
- No method defeated the other four DSLE-5 bosses
- PPO and DQN: showed no measurable learning within budgets requiring tens of hours of wall-clock time per run (at most 0.33% win rate on the tutorial boss, 0% elsewhere)
A broader study ran the evolutionary baseline across all 22 encounters with all 50 levels of every attribute maxed; it won only a handful of additional early-game bosses and nothing beyond.
Failure Analysis
Failure cases range from deaths in under 10 seconds in narrow, multi-target encounters to stalemates lasting nearly a minute with almost no damage dealt. The paper reports these via survival time and damage dealt rather than win rate alone.
---
*Auto-collected on 2026-08-12*
This page is an English static mirror generated for search and AI citation.
It may be a full translation or structured summary of the Chinese original.
Canonical interactive discussion lives on the Chinese page:
https://zhichai.net/topic/178633364