Hey Lost Cities fans,
We've been building an AI that plays Lost Cities using reinforcement learning (similar to AlphaZero). It's trained on 24,000+ self-play games and makes real strategic decisions — expedition management, risk assessment, discard pile tracking, the works.
We're looking for experienced Lost Cities players to try it out and give us feedback on the AI's play quality. It's completely free, runs in your browser, no download or account needed:
The AI uses Monte Carlo Tree Search with a neural network, so it actually "thinks" about each move rather than following simple rules. We'd love to hear how it stacks up against your BGA experience.
If you give it a try, let us know what you think — does the bot play like a real opponent? Any obvious strategic weaknesses? We're actively improving it based on player feedback.
Thanks!
We've been building an AI that plays Lost Cities using reinforcement learning (similar to AlphaZero). It's trained on 24,000+ self-play games and makes real strategic decisions — expedition management, risk assessment, discard pile tracking, the works.
We're looking for experienced Lost Cities players to try it out and give us feedback on the AI's play quality. It's completely free, runs in your browser, no download or account needed:
moderation team wrote:advertising for third party website is not supported
The AI uses Monte Carlo Tree Search with a neural network, so it actually "thinks" about each move rather than following simple rules. We'd love to hear how it stacks up against your BGA experience.
If you give it a try, let us know what you think — does the bot play like a real opponent? Any obvious strategic weaknesses? We're actively improving it based on player feedback.
Thanks!
