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

DSLE: A Dark Souls Boss-Encounter Learning Environment for Game Agents

Forum topic · 小凯 · 2026-08-11

Summary

The paper introduces the Dark Souls Learning Environment (DSLE), a containerized platform that exposes all 22 boss encounters of Dark Souls: Remastered as game-playing agent benchmarks via a Gymnasium-style interface. DSLE combines real-time combat, high-dimensional visual input, and sparse terminal rewards, with each step representing a real action executed against the running game. To support controlled comparison, the authors define DSLE-5, a representative five-boss subset covering melee combat, spatially constrained arenas, environmental hazards, multi-target fights, and a fast final boss. Evaluations on DSLE-5 include random policies, an expert system, an evolutionary baseline, and PPO and DQN agents trained from visual input. Expert and evolutionary baselines defeat the tutorial boss Asylum Demon at peak win rates of 63% and 43%, but none of the five methods beat the remaining four bosses. Results are reported via survival time and damage dealt, not just win rate.

Overview

Field: Machine Learning, Reinforcement Learning, Game AI Authors: Derin Gezgin, Jim O'Connor, Tanner Goodwin Published: 2026-08-11 arXiv: 2508.03798

Summary

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.
  • We recommend DSLE-5 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.
  • Key Findings

  • The expert system and evolutionary baseline each defeat the tutorial boss Asylum Demon (peak win rates of 63% and 43%, respectively).
  • None of the five methods defeat the other four bosses in DSLE-5.
  • PPO and DQN show no measurable learning within the wall-clock budget already requiring tens of hours per run (up to 0.33% win rate on the tutorial boss, 0% elsewhere).
  • A broader study running the evolutionary baseline across all 22 encounters, with overpowered level-50 stats, wins only a few additional early-game bosses; the rest remain unbeaten.
  • Failure cases range from deaths in under 10 seconds on cramped, multi-target encounters to nearly minute-long stalemates with minimal damage dealt.
  • Results are reported via survival time and damage dealt, not win rate alone, to capture partial progress.

Original 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.

Tags

#reinforcement-learning#game-ai#benchmark#dark-souls#ppo#dqn#evolutionary-baseline#gymnasium

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/178633342