AI News, Teaching computers to play Doom is a blind alley for AI – here’s an alternative
- On 3. juni 2018
- By Read More
Teaching computers to play Doom is a blind alley for AI – here’s an alternative
Games have long been used as testbeds and benchmarks for artificial intelligence, and there has been no shortage of achievements in recent months.
With the arrival of the latest techniques in AI and machine learning, attention is now shifting to visually detailed computer games – including the 3D shooter Doom, various 2D Atari games such as Pong and Space Invaders, and the real-time strategy game StarCraft.
Banana skins Getting computers to determine which actions even exist in a given context presents conceptual and practical challenges which games researchers have barely attempted to resolve so far.
In highlighting these problems, McCarthy said:“Our ultimate objective is to make programs that learn from their experience as effectively as humans do.” Until computers can tackle problems without any predetermined description of possible actions, this objective can’t be achieved.
Players were told about their environment by messages on the screen: They had to respond with simple instructions, usually in the form of a verb or a verb plus a noun – “look”, “take box” and so on.
More sophisticated behaviours on part of the computer would involve exploring the environment, defining goals, making goal-oriented action choices and solving the various intellectual challenges typically required to progress.
How well modern AI methods of the kind promoted by tech giants like IBM, Google, Facebook or Microsoft would fare in these text adventures is an open question – as is how much specialisthuman knowledge they would require for each new scenario.
Competitors submit entries in advance, and can use the AI technology of their choice to build programs that can play these games by making sense of a text description and outputting appropriate text commands in return.
Jerry Swan is asenior research fellow,Hendrik Baieris aresearch associate for artificial intelligence and data analytics, andTimothy Atkinson is adoctoral researcher at theUniversity of York.This article was first published in The Conversation (theconversation.com) The Independent's bitcoin group on Facebook is the best place to follow the latest discussions and developments in cryptocurrency.
- On 28. januar 2021
AI learns to play Asteroids
Using neuroevolution I trained an AI to play the game Asteroids and it nailed it. If you enjoy what I do and want more please consider supporting me on patreon ...
Google's DeepMind AI Just Taught Itself To Walk
Google's artificial intelligence company, DeepMind, has developed an AI that has managed to learn how to walk, run, jump, and climb without any prior guidance ...
MOBA's and the Future of AI Research | AI and Games
AI and Games is a crowdfunded show and needs your support. You can help fund this series on Paypal, KoFi and Patreon (where you can get access to ...
What Makes Good AI? | Game Maker's Toolkit
When we talk about good AI, we often think about highly efficient and aggressive enemies in shooters like FEAR and Halo. But surely there's more to good ...
MarI/O - Machine Learning for Video Games
MarI/O is a program made of neural networks and genetic algorithms that kicks butt at Super Mario World. Source Code: "NEAT" ..
These Google AI experiments are crazy! This is the future.
Google has some insane experimental AI - I figured it was worth exploring to see how close it is to destroying us all. Check them out yourself: ...
UC Berkeley Researcher made Vestri AI RobotTechnology that learns From own action See their Future😀
UC Berkeley Researcher made Vestri AI Robot that learns From own action See their Future Technology - The Daily Sheeple.Is it possible to make a robot that ...
Emergent Behavior in Game AI
In this microtalk from GDC 2013's 'Turing Tantrums' rant session, veteran Ben Sunshine-Hill describes how not wanting emergent behavior game AI means you ...
How researchers are teaching AI to learn like a child
Machine learning algorithms may need programmed instincts to gain common sense. Learn more: Credits ..
Build a Game AI - Machine Learning for Hackers #3
This video will get you up and running with your first game AI in just 10 lines of Python. The AI can theoretically learn to master any game you train it on, but has ...