AutoTavern agents build a Hearthstone AI that rivals top ladder players
In 20 days the system produced TavernGym and 23 TavernAgent versions whose last 20 games averaged 1.60 placement.
Stories per day · 30 days
2 RSS
Relatedaction-control1hearthstone1llm-agents1positional-encoding1reinforcement-learning1self-improvement1video-generation1world-models1
6 stories, newest first · one card per story
Stories tagged #game-ai
ActionRoPE encodes game actions as world-coordinate positions
Coordinate-conditioned noise scheduling cut revisit drift 66% versus the strongest of four baselines.
Faynt: Scaling and Optimizing Policies for Competitive Melee
Faynt's 10M Transformer wins 98.4% of same-character Super Smash Bros. Melee games against fourteen prior releases.
AI finally beat the best Stratego player in history—and did it on a budget
Researchers from CMU, MIT, NYU, and Stanford built Ataraxos, an AI that beat top Stratego player Pim Niemeijer 15-1 using only 16 GPUs.
PUBG Ally: A Conversational Embodied Agent as an AI Teammate
Researchers present PUBG Ally, a voice-enabled embodied teammate trained on nearly 39,000 live PUBG sessions.
A Qualitative Model for Reasoning about Path and Support
A hybrid qualitative reasoning model with center-of-mass stability logic enables explainable path-planning and stability guidance for the Camelot Jr. block-puzzle game.