We thank all the reviewers for the constructive comments. We address the major concerns below. Reproducibility: 1) learning to draft details; 2) feature details; 3) discussions on the computing resources used. The search tree is updated based on four steps of MCTS. The learning rate is set to 0.001 with Adam.

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 laptop. 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 ALE [4]. Using ELF, we thoroughly explore training parameters and show that a network with Leaky ReLU [17] and Batch Normalization [11] 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.

We formulate the problem of defogging as state estimation and future state prediction from previous, partial observations in the context of real-time strategy games.

We formulate the problem of defogging as state estimation and future state prediction from previous, partial observations in the context of real-time strategy games.

Effective coordination is crucial to solve multi-agent collaborative (MAC) problems.

Neural Information Processing Systems http://nips.cc/

We thank all the reviewers for the constructive comments. We address the major concerns below. Reproducibility: 1) learning to draft details; 2) feature details; 3) discussions on the computing resources used. The search tree is updated based on four steps of MCTS. The learning rate is set to 0.001 with Adam.

The article "Revelations: A Decidable Class of POMDP with Omega-Regular Objectives" won an Outstanding Paper Award at the AAAI 2025 conference, a prestigious international conference about artificial intelligence. This year, only three papers received such an award out of 3,000 accepted and 12,000 submitted! This recognition crowns the results of research initiated in Bordeaux (France) within the Synthèse team at the Bordeaux Computer Science Research Laboratory (LaBRI), where four of the authors work: Marius Belly, Nathanaël Fijalkow, Hugo Gimbert, and Pierre Vandenhove. The work also involved researchers from Paris (Florian Horn) and Antwerp (Guillermo A. Pérez). The article is freely available on arXiv, and this post outlines its main ideas.

StarCraft: Brood War remains a challenging benchmark for artificial intelligence research, particularly in the domain of macromanagement, where long-term strategic planning is required. Traditional approaches to StarCraft AI rely on rule-based systems or supervised deep learning, both of which face limitations in adaptability and computational efficiency. In this work, we introduce NeuroPAL, a neuroevolutionary framework that integrates Neuroevolution of Augmenting Topologies (NEAT) with Punctuated Anytime Learning (PAL) to improve the efficiency of evolutionary training. By alternating between frequent, low-fidelity training and periodic, high-fidelity evaluations, PAL enhances the sample efficiency of NEAT, enabling agents to discover effective strategies in fewer training iterations. We evaluate NeuroPAL in a fixed-map, single-race scenario in StarCraft: Brood War and compare its performance to standard NEAT-based training. Our results show that PAL significantly accelerates the learning process, allowing the agent to reach competitive levels of play in approximately half the training time required by NEAT alone. Additionally, the evolved agents exhibit emergent behaviors such as proxy barracks placement and defensive building optimization, strategies commonly used by expert human players. These findings suggest that structured evaluation mechanisms like PAL can enhance the scalability and effectiveness of neuroevolution in complex real-time strategy environments.

Blizzard's first real-time strategy games had a profound impact on me as a young immigrant to Canada in 1994 and '95. Warcraft: Orcs & Humans and Warcraft II: Tides of Darkness helped me learn how to read and write in English, and formed the basis for some of my oldest friendships in a brand-new country. Suffice to say, I have a lot of love for these old RTS games -- maybe more than Blizzard itself. So you can imagine my excitement at remaster rumors for Warcraft II and its expansion, Beyond the Dark Portal. When Blizzard aired its Warcraft Direct last week, not only were those rumors confirmed, but it announced that the original Warcraft would receive the same treatment, and both would be sold alongside Warcraft III: Reforged (itself a remaster) as part of a new battle chest.