Until it can learn for itself from scratch, building up intelligence on its own from its environment, it's a preprogrammed maze-searching algorithm. It was born knowing everything it ever needed to know. Maluuba's HRA is, in all honesty, a proof of concept. Hit the ball, shoot the thing, get a reward, figure it out, get better. These systems learned from scratch the value of their decisions.
MS PAC MAN TRIAL
Other reinforcement learning systems found out through hours of trial and error that, for example in Space Invaders, they could press the fire button and sometimes earn points that firing away made things disappear, also earning points that moving and firing made more things disappear, earning more points that moving to avoid being hit by enemy bullets let the player live longer, thus allowing it to gain more points and so on. It means the AI hasn't learned very much at all: it hasn't learned that ghosts are bad and to be avoided because they cause Ms Pac-Man to lose her lives and ultimately the whole game, that pills need to be collected, that fruits are good and not stationary ghosts, and so on. This is programmed in by the researchers. Pills and fruits are set a weight based on their in-game points. The crucial thing is that the reward weights are hardcoded into the software. She avoids the ghosts, she gets the pills and the fruit, and she gets the high score. So, for example, moving the character toward a ghost has a negative expected reward, whereas moving it toward a fruit or a line of pills has a very positive expected reward.Īt each step in time in the game, the oracle aggregates all the expected rewards from its sub-agents, and uses this information to move Ms Pac-Man in the directions that maximize the total reward. These values are used to calculate, for each object, an expected reward for the oracle agent if it moves Ms Pac-Man in the direction of that object. Pills and fruit get positive weights, whereas ghosts get negative weights. When the oracle agent finds a new object – a pellet, ghost or fruit – it creates a sub-agent representing that object and assigns it a fixed weight. This central oracle controls Ms Pac-Man's movements. Instead of a single bot trying to singlehandedly complete the game, the problem is shared between up to 163 sub-agents working in parallel for an oracle agent. The large number of possible states means it's difficult to generalize the complex environment for a single agent to tackle, Rahul Mehrotra, program manager at Maluuba, and Kaheer Suleman, cofounder and CTO of the upstart, explained to The Register.Ī paper published online on arXiv this week by Maluuba describes the team's winning Ms Pac-Man strategy, which uses something called a hybrid reward architecture (HRA) to pull off. Traditional reinforcement learning methods, which use a single agent player to tackle titles from Doom to StarCraft, are unsuitable for Ms Pac-Man. Some games are better suited to reinforcement learning than others – it's not a one-size-fits-all solution. And while chasing these rewards, the bot becomes stronger and stronger, making better and better moves, until it becomes rather good at the game.
MS PAC MAN CODE
Over time, the code works out which decisions and behaviors lead to more rewards. Here's how it works: every time a bot increases its score, typically by making a good move, it interprets this as a reward.
MS PAC MAN SOFTWARE
o8G0vreCEhĪt the moment, it's trendy to teach software agents to play games using reinforcement learning. beats Ms Pac-Man using unique reinforcement learning technique.
MS PAC MAN CRACKED
Now Maluuba, a Canadian AI biz pursuing general AI through language processing, and recently acquired by Microsoft, appears to have cracked the challenge of building a bot that can trump humans at Ms Pac-Man. The electronic player has to appreciate and master secondary goals – efficiently scouring a maze for pills, avoiding ghosts or eating them, strategically sacrificing a life to get a difficult-to-reach pellet, and so on – all to achieve an overall primary goal. It's not hard for an AI to find its way through a maze, but couple that with grabbing pills, dodging or eating ghosts, and collecting fruit for a high score, and it's suddenly tough work for an artificial brain. Computers can't play this game well, since there are just too many possible game states to consider – 10 77 configurations, apparently.
0 kommentar(er)
