How friendly is your AI?
Originally shared by Wayne Radinsky
How friendly is your AI? It depends on the rewards. "To study such scenarios, we modified DeepMind’s framework to allow two agents to share an environment and learn to either compete or collaborate. In our experiments we focused on the behaviour of the agents in well-known Pong game environment."
"In the competitive mode, the two agents were rewarded for putting the ball past the opponent. As we let the agents play against each other, both of them got better and better with time. Eventually the agents learned to ward off even difficult fast-flying shots and send the ball back with speed."
"In the collaborative game mode both agents were penalized (received negative rewards) whenever the ball went out of play. These were the only rewards the agents received. Starting from a random behaviour, agents quickly learned that the best way to avoid losing the ball is to never launch the ball in the first place."
http://robohub.org/how-friendly-is-your-ai-it-depends-on-the-rewards/
How friendly is your AI? It depends on the rewards. "To study such scenarios, we modified DeepMind’s framework to allow two agents to share an environment and learn to either compete or collaborate. In our experiments we focused on the behaviour of the agents in well-known Pong game environment."
"In the competitive mode, the two agents were rewarded for putting the ball past the opponent. As we let the agents play against each other, both of them got better and better with time. Eventually the agents learned to ward off even difficult fast-flying shots and send the ball back with speed."
"In the collaborative game mode both agents were penalized (received negative rewards) whenever the ball went out of play. These were the only rewards the agents received. Starting from a random behaviour, agents quickly learned that the best way to avoid losing the ball is to never launch the ball in the first place."
http://robohub.org/how-friendly-is-your-ai-it-depends-on-the-rewards/
Comments
Post a Comment