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

DSLE: A Gymnasium-Style Learning Environment for Dark Souls Boss Encounters

Forum topic · 小凯 · 2026-08-11

Summary

This paper introduces the Dark Souls Learning Environment (DSLE), a containerized benchmark that exposes all 22 boss encounters of Dark Souls: Remastered to game-playing agents through a Gymnasium-style interface. Each step is a real action executed against the running game, combining real-time combat, high-dimensional visual input, and sparse terminal rewards. The authors define DSLE-5, a five-boss subset spanning melee combat, spatially constrained arenas, environmental hazards, multi-target fights, and a fast final boss, recommended as a starting suite for new agents. Evaluations on DSLE-5 compare a random policy, an expert system, an evolutionary baseline, and PPO and DQN agents trained from visual input. The expert system and evolutionary baseline defeat the Asylum Demon tutorial boss at peak win rates of 63% and 43%, but none of the five methods defeat the remaining four bosses. PPO and DQN show no measurable learning within wall-clock budgets of dozens of hours per run, achieving at most 0.33% win rate on the tutorial boss and 0% elsewhere. Broader evaluation of the evolutionary baseline across all 22 encounters under favorable full-50-stat builds yields only a few additional early-game wins, with failure modes ranging from sub-10-second deaths to near one-minute stalemates with negligible damage.

Paper Overview

  • Field: Machine Learning (Reinforcement Learning Benchmarks)
  • Authors: Derin Gezgin, Jim O'Connor, Tanner Goodwin
  • Posted: 2026-08-11
  • arXiv: 2508.03798
  • Summary

    The authors introduce the Dark Souls Learning Environment (DSLE), a containerized benchmark platform that exposes all 22 boss encounters of *Dark Souls: Remastered* to game-playing agents through a Gymnasium-style interface. DSLE combines three challenging properties for RL research:

  • Real-time combat
  • High-dimensional visual input
  • Sparse terminal rewards
  • Each environment step corresponds to a real action executed against the running game, rather than a simulator abstraction.

    DSLE-5 Benchmark Subset

    To support controlled comparison, the authors define DSLE-5, a representative five-boss subset covering distinct combat archetypes:

    1. Melee fight 2. Spatially constrained arena 3. Environmental-hazard fight 4. Multi-target fight 5. Fast final-boss fight

    DSLE-5 is recommended as the starting suite for agents built on DSLE.

    Evaluated Methods

    On DSLE-5, five approaches were evaluated:

  • Random policy
  • Expert system
  • Evolutionary baseline
  • PPO (Proximal Policy Optimization) trained from visual input
  • DQN (Deep Q-Network) trained from visual input
  • Key Results

  • The expert system and evolutionary baseline each defeat the Asylum Demon tutorial boss, with peak win rates of 63% and 43% respectively.
  • None of the five methods defeat the remaining four DSLE-5 bosses.
  • PPO and DQN show no measurable learning within wall-clock budgets of dozens of hours per run:
  • At most 0.33% win rate on the tutorial boss
  • 0% win rate on the other four bosses
  • A broader study running the evolutionary baseline across all 22 encounters under favorable full-50-stat builds wins only a few additional early-game bosses, with all remaining encounters lost.
  • Failure Modes

    The authors report failures not only via win rate but also via survival time and damage dealt. Failure cases include:

  • Deaths in under 10 seconds in cramped, multi-target encounters
  • Stalemates lasting nearly one minute with negligible damage inflicted

Conclusion

DSLE provides a challenging, real-game benchmark for reinforcement learning research, and current standard methods (PPO, DQN, evolutionary baselines) are far from solving it, even on a reduced five-boss suite.

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

Tags

#reinforcement-learning#benchmark#dark-souls#game-ai#ppo#dqn#gymnasium#arxiv-2508-03798

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/178633354