PulseAugur
EN
LIVE 08:59:10

AI agent achieves 51.35% win rate against champion using unsound search

By PulseAugur Editorial · [1 sources] ·

Researchers have developed an agent for the collectible card game Legends of Code and Magic that utilizes unsound search techniques to achieve a win rate of 51.35% against the game's champion, ByteRL. This agent, named NeteaseOPD, was trained using imitation learning and a policy and value feed-forward network, and it demonstrated a significant improvement of +24.6 percentage points in win rate when search was incorporated. Furthermore, the agent showed increased resilience against a published best-response attack compared to ByteRL. AI

IMPACT Demonstrates that unsound search can be effective in complex imperfect information games, potentially influencing future game AI development.

RANK_REASON Academic paper detailing a novel approach to game AI. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

AI agent achieves 51.35% win rate against champion using unsound search

How we ranked this

Signal score
15 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Academic paper detailing a novel approach to game AI. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. arXiv cs.AI TIER_1 English(EN) · Dustin Rubin ·

    Unsound Search with Policy and Value Networks in Legends of Code and Magic

    arXiv:2609.06816v1 Announce Type: new Abstract: Decision-time search in perfect and imperfect information games with enumerable belief states are effective methods for game AI. Collectible card games are imperfect information games with large belief states. Legends of Code and Ma…

RELATED ENTITIES

RELATED TOPICS