Your video, Scientists taught rats to drive little cars for Froot Loops, has made it into the Top 15 New Videos listing. Congratulations on your achievement. For your contribution you have been awarded 1 Power Point.

Edison was a well known patent and credit thief.

I find it ridiculously suspicious that he "invented" the phonograph shortly after the invention of the exceptionally similar paleophone. Charles Cros submitted a sealed envelope containing a letter to the Academy of Sciences on April 30, 1877 detailing the design of the paleophone, the first device capable of recording and playing the recording back as sound, later that year an account of his invention was published on October 10, 1877 a month before Edison claimed credit, then Edison patented it the next year..
Suspicious to say the least if you consider how many other inventions he "invented" after someone else had already done so....like the light bulb.

Edison always seemed like the Trump of late 1800's inventors imo, constantly taking credit for other people's work, patenting their inventions without even crediting them, and was a total shady but successful business man thanks to a total lack of ethics.

Wizard of Menlo Park? Please. Just another backstabbing rat from New Jersy if you ask me.

I'm team Tesla all day long. ;-)

This isn't really true though and greatly understates how amazing this demo, and current AI actually is.

Saying the agents are obeying a set of human defined rules / freedoms / constraints and objective functions would lead one to imagine something more like video game AI.

Typically video game AI works on a set of weighted decisions and actions, where the weights, decisions and actions are defined by the developer; a more complex variation of:

if my health is low, move towards the health pack,
otherwise, move towards the opponent

In this demo, no such rules exist. It's not given any weights (health), rules (if health is low), nor any instructions (move towards health pack). I guess you could apply neural networks to traditional game AI to determine the weights for decision making (which are typically hard coded by the developer); but that would be far less interesting than what's actually happening here.

Instead, the agent is given a set of inputs, a set of available outputs, and a goal.

4 Inputs:
- Position of the agent itself
- Position and type (other agent, box, ramp) of objects within a limited forward facing conical view
- Position (but not type) of objects within a small radius around the agent
- Reward: Whether they are doing a good job or not

Note the agent is given no information about each type of object, or what they mean, or how they behave. You may as well call them A, B, C rather than agent, box, ramp.

3 Outputs:
- Move
- Grab
- Lock

Again, the agent knows nothing about what these mean, only that they can enable and disable each at any time. A good analogy is someone giving you a game controller for a game you've never played. The controller has a stick and two buttons and you figure out what they do by using them. It'd be accurate to call the outputs: stick, A, B rather than move, grab, lock.

Goal:
- Do a good job.

The goal is simply for the reward input to be maximised. A good analogy is saying 'good girl' or giving a treat to a dog that you are training when they do the right thing. It's up to the dog to figure out what it is that they're doing that's good.

The reward is entirely separate from the agent, and agent behaviour can be completely changed just by changing when the reward is given. The demo is about hide and seek, where the agents are rewarded for not being seen / seeing their opponent (and not leaving the play area). The agents also succeeded at other games, where the only difference to the agent was when the reward was given.

It isn't really different from physically building the same play space, dropping some rats in it, and rewarding them with cheese when they are hidden from their opponents - except rats are unlikely to figure out how to maximise their reward in such a 'complex' game.

Given this description of how the AI actually works, the fact they came up with complex strategies like blocking doors, ramp surfing, taking the ramp to stop their opponents from ramp surfing, and just the general cooperation with other agents, without any code describing any of those things - is pretty amazing.

You can find out more about how the agents were trained, and other exercises they performed here:

https://openai.com/blog/emergent-tool-use/

That's why it's called The USA's National Pass-out...er... I mean Pastime. I jest, I jest!

But hey, I spent my two-minute in this video looking for rats... and I failed to see any... how can this be?!

Props to the little girls for not ratting him out.

Stick it to the Man!

Yeah, this doesn't seem very practical. The mink in particular I can't see killing enough to make a difference the way they're deploying it. The dogs might, though, if they live on the farm and kill rats all day.

Your video, John Waters Reveals How He Got Rats to Have Sex for His Film, has made it into the Top 15 New Videos listing. Congratulations on your achievement. For your contribution you have been awarded 1 Power Point.

The Doomed Mouse Utopia That Inspired the 'Rats of NIMH' has been added as a related post - related requested by ant.

*related=http://videosift.com/video/The-Doomed-Mouse-Utopia-That-Inspired-the-Rats-of-NIMH

Ya, just watched the first flight episode again. Drogon chowed down and ripped a Son of the Harpy in two like a terrier with a rat.

Good times.

Holy crap S8 ep 5 made 0 fucking sense. I hate when writers run out of ideas. Awesome effects, but no narrative fucks were given.

*dupeof=http://videosift.com/video/Ninja-rat-spin-kicks-a-rattlesnake

1 more comment have been lost in the ether at this killed duplicate.

This video has been declared a duplicate by the original submitter; transferring votes to the original video and killing this dupe - dupeof declared by ant.

Your video, Ninja rat spin kicks a rattlesnake, has made it into the Top 15 New Videos listing. Congratulations on your achievement. For your contribution you have been awarded 1 Power Point.

Can't call him a dirty rat.