Deal or no deal? Training AI bots to negotiate
code.facebook.com
Deal or no deal? Training AI bots to negotiate
1–10 of 17 posts
Re: Deal or no deal? Training AI bots to negotiate
#2The most interesting thing to me is not the negotiation tactics that the agents learn but the idea of coming up with a more easily quantifiable (and therefore differentiable) quality metric for dialogue tasks.
Re: Deal or no deal? Training AI bots to negotiate
#3Interesting that the chatbots learned to show "fake" interest in an item, just to conceide it later in the negotiation process.
But I think what is missing, is the time component when negotiating with humans. A negotiation process is usually better for humans if the negotiation is quick and not dragging on too long.
And more importantly the chatbots never seemed to "walk away" from a deal. But in real life, you sometimes have to walk away to show the other party, that you are not a pushover. It would be interesting to enhance the model so that chatbots negotiate repeatedly with each other and "remember" how the other party behaves and how far you can push the other party to concede. Because some negotiations really are zero sum games.
Re: Deal or no deal? Training AI bots to negotiate
#4Interesting that the chatbots learned to show "fake" interest in an item, just to conceide it later in the negotiation process. But I think what is missing, is the time component when negotiating with humans. A negotiation process is usually better for humans if the negotiation is quick and not dragging on too long. And more importantly the chatbots never seemed to "walk away" from a deal. But in real life, you somet…
> But in real life, you sometimes have to walk away to show the other party, that you are not a pushover.
AI consider this human behavior a bug.
Re: Deal or no deal? Training AI bots to negotiate
#5It'd be interesting if the agents developed their own language during the reinforcement learning stage that is unintelligible to humans but allows them to quickly navigate the negotiation. They use the model trained in a supervised way during the reinforcement learning stage to avoid this, but I'm curious to see what the agent learns when paired against another reinforcement learning agent.
Edit: Indeed, the paper says that not using the fixed agent trained on human negotiation leads to unintelligible language from the agents.
Re: Deal or no deal? Training AI bots to negotiate
#6Interesting that the chatbots learned to show "fake" interest in an item, just to conceide it later in the negotiation process. But I think what is missing, is the time component when negotiating with humans. A negotiation process is usually better for humans if the negotiation is quick and not dragging on too long. And more importantly the chatbots never seemed to "walk away" from a deal. But in real life, you somet…
> But in real life, you sometimes have to walk away to show the other party, that you are not a pushover. AI consider this human behavior a bug.
Not really, there are some situations where the deal is too heavily skewed for it to be favorable for you. In human terms "I'm not willing to pay this much for this". What AI might actually consider bugs would be stuff like politeness or pity (I can't refuse to buy from this small hungry child), basically things external to the actual process of negotiation, but that might have considerable impact on human agents and how they would feel afterwards. (for example giving money to a beggar is a one-way act, but the donor will likely feel good about themselves despite not getting any material gains) Similarly, people might purposefully adjust their tactics depending on the status of who they are negotiating with, making more concessions with family and friends. If the AI just looks at the inherent value of the items, it'll miss things like that.
Re: Deal or no deal? Training AI bots to negotiate
#7>To prevent the algorithm from developing its own language, it was simultaneously trained to produce humanlike language.
Not sure what this would look like, but I'd be interested to find out.
Re: Deal or no deal? Training AI bots to negotiate
#8Interesting that the chatbots learned to show "fake" interest in an item, just to conceide it later in the negotiation process. But I think what is missing, is the time component when negotiating with humans. A negotiation process is usually better for humans if the negotiation is quick and not dragging on too long. And more importantly the chatbots never seemed to "walk away" from a deal. But in real life, you somet…
I bet you could make a walking away function with a threshold and that would trigger a iterated prisoner dilemma subroutine.
Re: Deal or no deal? Training AI bots to negotiate
#9Interesting that the chatbots learned to show "fake" interest in an item, just to conceide it later in the negotiation process. But I think what is missing, is the time component when negotiating with humans. A negotiation process is usually better for humans if the negotiation is quick and not dragging on too long. And more importantly the chatbots never seemed to "walk away" from a deal. But in real life, you somet…
> But in real life, you sometimes have to walk away to show the other party, that you are not a pushover. AI consider this human behavior a bug.
No, it's signaling that you're wasting time and need to move on.
Many situations cannot be resolved until you convince the other party that their business model or position or assumptions are wrong. Walking away is the only way to do that because it triggers escalation.
I had s sitstuiin recently where the account team couldn't get a term that we needed. We basically told them to go away and stopped 2-3 other negotiations. That let our counterparty get the resource he needed (SVP of product X) and balance returned to the force.
Re: Deal or no deal? Training AI bots to negotiate
#10So in a very limited sense these agents have a theory of mind - they can infer the beliefs and goals of their opponents and act accordingly. Agents/objects can be in an exponential number of possible relative positions, but this system factorizes structure from function.