RECONNAISSANCE BLIND CHESS
Join the RBC Research Community
Online Competition is Live
Prizes will be awarded to the owners of the bots with the highest ranks on August 31, 2020 11:59 pm EDT:
1st Place: $1000
2nd Place: $500
NeurIPS 2019 Tournament
Congratulations to the participants of our NeurIPS 2019 tournament!
A Challenge for Machine Decision Making under Uncertainty
Many of the favorite studied games in artificial intelligence (AI) such as checkers, chess, and Go lack something that is extremely common and critical in real-life decision making: uncertainty. Other popular games like poker lack a significant component of long term strategy or planning.
Reconnaissance blind chess (RBC) is like chess except a player cannot see where her opponent's pieces are a priori. Rather, she learns partial information about them through chosen sensing actions and the results of moves.
Compared to phantom games like Kriegspiel and games like dark chess, in RBC players have much more ability to manage their uncertainty with explicit sensing actions, which we believe makes the game more interesting from an AI perspective and more realistic for many scenarios; players are not completely blind, but rather, metaphorically, they simply cannot look everywhere at once.
Join the study and fun now by building a bot.
Current Bot Leaderboard
|Rank||User||Rating||Num Ranked Matches|