Researchers have developed the Dark Souls Learning Environment (DSLE), a platform designed to benchmark AI agents against the boss encounters in Dark Souls: Remastered. The environment provides a Gymnasium-style interface, real-time combat, and visual input, with each step representing an action within the game. A recommended five-boss subset, DSLE-5, was used to evaluate various agents, including Proximal Policy Optimization (PPO) and Deep Q-Network (DQN) models, which showed no significant learning progress within a substantial computational budget. AI
IMPACT This benchmark could spur advancements in AI's ability to handle complex, visually-driven tasks with sparse rewards.
RANK_REASON The item is an academic paper detailing a new benchmark environment for AI research. [lever_c_demoted from research: ic=1 ai=1.0]
Read on arXiv cs.NE (Neural & Evolutionary) →
- arXiv
- Asylum Demon
- Dark Souls: Remastered
- Deep Q-Network
- DSLE-5
- gymnasium
- Proximal Policy Optimization
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
