# ELF: An Extensive, Lightweight and Flexible Research Platform for Real-time Strategy Games

arXiv: https://arxiv.org/abs/1707.01067 · HTML: https://mlsanity.com/paper/1707.01067/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jul 2017.

## Built on by (most cited first, 17 of 17)

- [TorchRL: A data-driven decision-making library for PyTorch](https://mlsanity.com/paper/2306.00577/) (2023)
- [MALib: A Parallel Framework for Population-based Multi-agent Reinforcement Learning](https://mlsanity.com/paper/2106.07551/) (2021)
- [RecSim NG: Toward Principled Uncertainty Modeling for Recommender Ecosystems](https://mlsanity.com/paper/2103.08057/) (2021)
- [Gym-μRTS: Toward Affordable Full Game Real-time Strategy Games Research with Deep Reinforcement Learning](https://mlsanity.com/paper/2105.13807/) (2021)
- [Alexa Arena: A User-Centric Interactive Platform for Embodied AI](https://mlsanity.com/paper/2303.01586/) (2023)
- [On Efficient Reinforcement Learning for Full-length Game of StarCraft II](https://mlsanity.com/paper/2209.11553/) (2022)
- [Triple-GAIL: A Multi-Modal Imitation Learning Framework with Generative Adversarial Nets](https://mlsanity.com/paper/2005.10622/) (2020)
- [WarpDrive: Extremely Fast End-to-End Deep Multi-Agent Reinforcement Learning on a GPU](https://mlsanity.com/paper/2108.13976/) (2021)
- [Emergent collective intelligence from massive-agent cooperation and competition](https://mlsanity.com/paper/2301.01609/) (2023)
- [TowerMind: A Tower Defence Game Learning Environment and Benchmark for LLM as Agents](https://mlsanity.com/paper/2601.05899/) (2026)
- [Understanding Game-Playing Agents with Natural Language Annotations](https://mlsanity.com/paper/2204.07531/) (2022)
- [AMaze: An intuitive benchmark generator for fast prototyping of generalizable agents](https://mlsanity.com/paper/2411.13072/) (2024)
- [Optimize Neural Fictitious Self-Play in Regret Minimization Thinking](https://mlsanity.com/paper/2104.10845/) (2021)
- [AI planning in the imagination: High-level planning on learned abstract search spaces](https://mlsanity.com/paper/2308.08693/) (2023)
- [PerOS: Personalized Self-Adapting Operating Systems in the Cloud](https://mlsanity.com/paper/2404.00057/) (2024)
- [Monopoly Deal: A Benchmark Environment for Bounded One-Sided Response Games](https://mlsanity.com/paper/2510.25080/) (2025)
- [Learning to Play: Reinforcement Learning and Games](https://mlsanity.com/paper/2610.17391/) (2026)

## Abstract (arXiv)

In this paper, we propose ELF, an Extensive, Lightweight and Flexible platform for fundamental reinforcement learning research. Using ELF, we implement a highly customizable real-time strategy (RTS) engine with three game environments (Mini-RTS, Capture the Flag and Tower Defense). Mini-RTS, as a miniature version of StarCraft, captures key game dynamics and runs at 40K frame-per-second (FPS) per core on a Macbook Pro notebook. When coupled with modern reinforcement learning methods, the system can train a full-game bot against built-in AIs end-to-end in one day with 6 CPUs and 1 GPU. In addition, our platform is flexible in terms of environment-agent communication topologies, choices of RL methods, changes in game parameters, and can host existing C/C++-based game environments like Arcade Learning Environment. Using ELF, we thoroughly explore training parameters and show that a network with Leaky ReLU and Batch Normalization coupled with long-horizon training and progressive curriculum beats the rule-based built-in AI more than 70% of the time in the full game of Mini-RTS. Strong performance is also achieved on the other two games. In game replays, we show our agents learn interesting strategies. ELF, along with its RL platform, is open-sourced at https://github.com/facebookresearch/ELF.