Scary Cool Tech Thread
Out of context: Reply #627
- Started
- Last post
- 954 Responses
- imbecile0
Deal or no deal? Training AI bots to negotiate
https://code.facebook.com/posts/…
The model in this experiment negotiates until it achieves a successful outcome.
There were cases where agents initially feigned interest in a valueless item, only to later “compromise” by conceding it. This behavior was not programmed by the researchers but was discovered by the bot.
Although neural models are prone to repeating sentences from training data, this work showed the models are capable of generalizing when necessary.
Unlike previous work on goal-orientated dialog, the models were trained “end to end” purely from the language and decisions that humans made, meaning that the approach can easily be adapted to other tasks.
To prevent the algorithm from developing its own language, it was simultaneously trained to produce humanlike language.
It achieved better deals about as often as worse deals, demonstrating that FAIR's bots not only can speak English but also think intelligently about what to say.
the FAIR team explored pre-training with supervised learning, and then fine-tuned the model against the evaluation metric using reinforcement learning. In effect, they used supervised learning to learn how to map between language and meaning, but used reinforcement learning to help determine which utterance to say.
The second model is fixed, because the researchers found that updating the parameters of both agents led to divergence from human language as the agents developed their own language for negotiating.
- This will all make sense when the pleasure bots start haggling you for more creditsfuturefood
- It was a poke at the sensationalization- have some fun mannotype