English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

DSLE: A Learning Environment for Dark Souls Boss Encounters (arXiv 2508.05142)

Forum topic · 小凯 · 2026-08-12

Summary

Researchers introduce the Dark Souls Learning Environment (DSLE), a containerized platform exposing all 22 boss encounters from Dark Souls: Remastered as benchmarks for game-playing AI agents via a Gymnasium-style interface. DSLE combines real-time combat, high-dimensional visual input, and sparse terminal rewards, with each environment step corresponding to a real action executed against the running game. For 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. Baseline evaluations on DSLE-5 included a random policy, an expert system, an evolutionary baseline, and PPO and DQN agents trained from visual input. Expert systems and evolutionary baselines could beat the tutorial boss, the Asylum Demon (peak win rates of 63% and 43% respectively), but no method defeated the other four DSLE-5 bosses; PPO and DQN showed no measurable learning despite budgets of tens of wall-clock hours per run. A broader study running evolutionary baselines across all 22 fights with 50 character levels yielded only a few additional early-game wins. The paper reports survival time and damage dealt alongside win rate. Full paper: arXiv:2508.05142.

Paper Overview

Research area: Machine Learning Authors: Derin Gezgin, Jim O'Connor, Tanner Goodwin Published: 2026-08-12 arXiv: 2508.05142

Introduction

This paper presents the Dark Souls Learning Environment (DSLE), a containerized platform that turns all 22 boss encounters of *Dark Souls: Remastered* into game-playing agent benchmarks through a Gymnasium-style interface.

Key properties of DSLE

  • Real-time combat combined with high-dimensional visual input
  • Sparse, terminal-only rewards
  • Every environment step is a real action executed against the running game
  • DSLE-5 benchmark subset

    To support controlled comparison, the authors define DSLE-5, a representative five-boss subset recommended as the starting suite for agents built on DSLE:

    1. A melee fight 2. A spatially constrained arena 3. An environmental-hazard fight 4. A multi-target fight 5. A fast final-boss fight

    Evaluation Results on DSLE-5

    The authors evaluate a random policy, an expert system, an evolutionary baseline, and PPO and DQN agents trained from visual input:

  • Expert systems and evolutionary baselines can each defeat the tutorial boss, the Asylum Demon, with peak win rates of 63% and 43% respectively
  • None of the five methods can defeat the other four DSLE-5 bosses
  • PPO and DQN agents show no measurable learning even with budgets of tens of wall-clock hours per run (at most 0.33% win rate on the tutorial boss, 0% elsewhere)
A broader study runs the evolutionary baseline across all 22 fights, sweeping all 50 level-up attributes; it achieves wins only on a few additional early bosses.

Failure modes range from dying within 10 seconds in narrow multi-target fights, to stalemates lasting nearly a minute while dealing almost no damage.

Reporting Metrics

Because win rate alone is too coarse, the paper also reports results in terms of survival time and damage dealt.

Original Abstract (excerpt)

> 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 vi...

Paper link: <https://arxiv.org/abs/2508.05142>

--- *Auto-collected on 2026-08-12*

Tags

#machine-learning#reinforcement-learning#dark-souls#game-ai#benchmark#ppo#dqn#arxiv

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/178633376