paper-with-me

Papers

Superhuman AI for Generals.io Using Self-Play Reinforcement Learning

2026-06-22 · Matej Straka, Viliam Lisý, Martin Schmid arxiv

We present a superhuman AI agent for Generals.io, a real-time strategy game that requires both long-horizon planning and short-term tactics under strong imperfect information. Trained for four days on 4x NVIDIA H200 GPUs, our agent reaches #1 on the public 1v1 leaderboard of over 5,000 human players, leading the second-ranked player by the same margin that separates second place from 25th, and beats the two top-ranked humans head-to-head with a combined 199-70 record across 269 ladder matches. A key enabler is a JAX-native simulator that reaches tens of millions of frames per second on a single GPU, roughly a 10,000x speedup over the prior simulator. On top of this, we train a vision transformer policy end-to-end by self-play with a policy-gradient loop and sparse win/loss reward, using top-advantage sample filtering and an exponential moving average of the policy parameters. Taken together, our findings highlight what matters, and what does not, once a fast simulator removes the data bottleneck.

📄 PDF Abstract BibTeX arXiv:2606.23348

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Artificial Generals Intelligence: Mastering Generals.io with Reinforcement Learning

2025-07-09 · Matej Straka, Martin Schmid

We introduce a real-time strategy game environment built on Generals.io, a game that hosts thousands of active players each week across multiple game formats. Our environment is fully compatible with Gymnasium and Pettin…

GPUMulti-agent Reinforcement Learningreinforcement-learningReinforcement Learning

Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm

2017-12-05 · David Silver, Thomas Hubert, Julian Schrittwieser, Ioannis Antonoglou 외

The game of chess is the most widely-studied domain in the history of artificial intelligence. The strongest programs are based on a combination of sophisticated search techniques, domain-specific adaptations, and handcr…

Game of ChessGame of GoGame of ShogiGeneral Reinforcement Learning+3

Superhuman AI for Stratego Using Self-Play Reinforcement Learning and Test-Time Search

2025-11-10 · Samuel Sokota, Eugene Vinitsky, Hengyuan Hu, J. Zico Kolter 외 arxiv

Few classical games have been regarded as such significant benchmarks of artificial intelligence as to have justified training costs in the millions of dollars. Among these, Stratego -- a board wargame exemplifying the c…

Reinforcement LearningDecision Making

Deep Reinforcement Learning from Self-Play in Imperfect-Information Games

2016-03-03 · Johannes Heinrich, David Silver

Many real-world applications can be described as large-scale games of imperfect information. To deal with these challenging domains, prior work has focused on computing Nash equilibria in a handcrafted abstraction of the…

Card GamesDeep Reinforcement LearningGame of Pokerreinforcement-learning+2

Provable Self-Play Algorithms for Competitive Reinforcement Learning

2020-02-10 · ICML 2020 1 · Yu Bai, Chi Jin

Self-play, where the algorithm learns by playing against itself without requiring any direct supervision, has become the new weapon in modern Reinforcement Learning (RL) for achieving superhuman performance in practice. …

reinforcement-learningReinforcement LearningReinforcement Learning (RL)