Categories: NewsTechnology

Microsoft’s New AI Reaches High Score in Ms. Pac-Man

There appears to be a rather strange correlation between artificial intelligence and gaming right now. We have seen AIs take on players in Go, and Microsoft is now tackling the infamous Ms. Pac-Man game. Their new AI has claimed the top score in this particular game, which makes it four times better than the top-ranking human player. All of this shows us humans are not necessarily the greatest at video games, unfortunately.

Ms. Pac-Man High Score Smashed By An AI

It is not entirely surprising to learn artificial intelligence solutions are better at playing particular video games compared to most humans. After all, we humans are great at doing several things quite well, whereas an AI can excel at doing just one thing better than anything else. In this particular case, Microsoft’s new AI has thrashed all human players when it comes to Ms. Pac-Man, as it successfully reached the top score possible. An impressive feat, although some people may not be too happy about it.

To put this news into perspective, reaching the top score in Ms. Pac-Man is no easy feat, not even for an AI. In fact, experts felt his particular game is the hardest to beat for an artificial intelligence. There is a lot going on at the same time, and the circumstances of the game can shift around quite a bit. Interestingly enough, Microsoft’s concoction was more than capable of handling the pressure and made playing the game look like a walk in the park.

The AI in question is developed by Maluuba, a Canadian deep learning startup owned by Microsoft. The company was acquired earlier in 2017, and it appears Microsoft has made a smart move in doing so. Beating the Ms. Pac-Man game is the company’s first major feat, but it certainly is one that will go down in the history books. In comparison, the best human player to date scored four times fewer points in the game.

Related Post

Under the hood, the AI used a method described as Hybrid Reward Architecture. It is a combination of reinforcement learning algorithms. By training around 150 individual AI agents to work together in parallel, the team successfully ensured its creation could reach the top score. All agents were rewarded for eating pellets, whereas others were trained to avoid ghosts. Combining all of these experiences into one project lead to this unexpected success.

The world of video games is slowly being dominated by artificial intelligence these days. Google’s AlphaGo thrashed the world champion not too long ago and promptly announced retirement. Now that Microsoft’s project has beaten Ms. Pac-Man, it is doubtful the AI will play this game ever again. Once the maximum result is achieved, there is no reason for these AI creations to keep playing the same game, as there is no further room for significant improvement.

The fact an AI can defeat a rather unpredictable game with such ease is rather telling, though. It is evident artificial intelligence is incredibly powerful at this stage, at least where these single-player games are concerned. It will take some time until we see an AI be successful in competitive multiplayer games, though, but it may happen at some point.

If you liked this article, follow us on Twitter @themerklenews and make sure to subscribe to our newsletter to receive the latest bitcoin, cryptocurrency, and technology news.

JP Buntinx

JP Buntinx is a FinTech and Bitcoin enthusiast living in Belgium. His passion for finance and technology made him one of the world's leading freelance Bitcoin writers, and he aims to achieve the same level of respect in the FinTech sector.

Share
Published by
JP Buntinx
Tags: AIGaming

Recent Posts

Supreme Court Strikes Down Trump Emergency Tariffs In Landmark Ruling Limiting Executive Trade Powers

In a landmark decision that reshapes U.S. trade policy, the Supreme Court of the United…

1 day ago

USDT Supply Decline Marks Biggest Contraction Since FTX Era

The global stablecoin market is entering a new phase of recalibration as the circulating supply…

1 day ago

xStocks Surpasses $25 Billion Volume As Tokenized Equities Enter New Market Phase

The tokenized equities sector is accelerating rapidly, and xStocks has now crossed a defining milestone:…

2 days ago

Base Begins Transition To Native Tech Stack In Major Layer 2 Shift

Coinbase-incubated Layer 2 network Base is entering a new phase of its development, moving toward…

2 days ago

Zora Officially Launches Its Revolutionary “Attention Market” On Solana In A Bold Multichain Expansion

Zora has officially launched its new “attention market” on the Solana blockchain, marking a bold…

3 days ago

XRP Ledger Activates Permissioned DEX With XLS-81 As Institutional Trading Model Emerges

The XRP Ledger has introduced a new on-chain trading framework that signals a notable shift…

3 days ago