I like the focus on vector space.
Obstacles on the Path to AI
11–20 of 31 posts
Re: Obstacles on the Path to AI
#12Earlier quoted context omitted.
He's saying you won't learn billions is parameters with RL /alone/ because "one scalar reward per trial isn't going to cut it". I find that convincing and a key insight. RL is going to be fundamental to AGI, but he's saying curiosity / unsupervised learning will be necessary. And I say this as a big believer in the need for more work on RL.
Yes, I should have added the context about the scalar reward, but I'm not sure why that changes anything. This may seem like a naive question, but it's sincere: What makes a scalar reward less effective at modifying a Q function than a scalar error that's used in backprop and assigned to a neural network's coefficients?
The error in backprop is a vector quantity, not a single scalar for each time step. In RL the goal is to optimize the overall sum of the reward over all time steps. Backprop attempts to minimize the magnitude of the error for a given loss function, by moving in the negative direction of the gradient of the function. Backprop just moves a lot more variables to a desired outcome, that is what LeCun is saying. The representational power of a single scalar 'score' doesn't have much ability to optimize such a large n-dimensional function in any efficient way.
Re: Obstacles on the Path to AI
#13Earlier quoted context omitted.
He's saying you won't learn billions is parameters with RL /alone/ because "one scalar reward per trial isn't going to cut it". I find that convincing and a key insight. RL is going to be fundamental to AGI, but he's saying curiosity / unsupervised learning will be necessary. And I say this as a big believer in the need for more work on RL.
Yes, I should have added the context about the scalar reward, but I'm not sure why that changes anything. This may seem like a naive question, but it's sincere: What makes a scalar reward less effective at modifying a Q function than a scalar error that's used in backprop and assigned to a neural network's coefficients?
The point is that supervised training on large networks requires millions or billions of examples. In RL, that means potentially billions of execution trajectories, which can be really expensive if you're executing on an actual, physical robot. And even then, supervised classification objectives are more informative than just a scalar reward: when a supervised system makes a wrong prediction you don't just tell it "sorry, that's wrong", you also tell it what the right prediction would have been. That extra information is really valuable for learning.
In the black-box RL setting, you only see whether what you did was right or wrong, not what the right thing would have been to do. And unlikely a classification system where the output space is relatively small (ImageNet has 1000 classes), an RL agent is searching over an exponentially large space of possible trajectories. Which means that without some additional source of supervision you can spend a long time wandering in the wilderness with no idea of whether what you're doing is reasonable or how to get any reward at all. And when you do get some reward, you have no idea which of the possibly hundreds or thousands of actions you took deserves the credit.
A lot of recent RL research is about finding additional sources of supervision, such as training an agent to mimic the policy of an "expert" (e.g., a search algorithm that runs in a simulator to find an optimal solution, but which requires too much computation to actually apply directly at test time, as in http://arxiv.org/abs/1504.00702), or coming up with proxy objectives like "empowerment" or "curiosity" (which you can define in terms of information theoretic quantities, such as mutual information between the agents' action sequence and future state, e.g. http://arxiv.org/abs/1509.08731) to supplement the actual reward signal. This latter path, the notion of "intrinsic reward" that paulsutter alluded to, is in some sense the merger of RL with unsupervised learning, and a lot of the power is that you're getting new reward signals constantly, not just when you finally manage to achieve some arbitrarily difficult task.
Re: Obstacles on the Path to AI
#14Everytime I read something like this, I get sad that I don't understand most of it. But then I get happy because at least I understand a little bit :)
Reading some random slides from a specialist talk is not exactly the easiest way to learn this stuff.
Re: Obstacles on the Path to AI
#15Earlier quoted context omitted.
Yes, I should have added the context about the scalar reward, but I'm not sure why that changes anything. This may seem like a naive question, but it's sincere: What makes a scalar reward less effective at modifying a Q function than a scalar error that's used in backprop and assigned to a neural network's coefficients?
The error in backprop is a vector quantity, not a single scalar for each time step. In RL the goal is to optimize the overall sum of the reward over all time steps. Backprop attempts to minimize the magnitude of the error for a given loss function, by moving in the negative direction of the gradient of the function. Backprop just moves a lot more variables to a desired outcome, that is what LeCun is saying. The repre…
Maybe I'm thinking about things wrong, but can't you have a scalar quantity to represent error for backprop at the end of a neural network (in a supervised regression problem for example)? That scalar error becomes a vector as it is assigned to various weights. I'm not trying to be obtuse, but it seems like the scalar reward in RL is also modifying countless variables in the Q functions of the state-action pairs that led to the final outcome/reward... Are those, by definition, smaller in number than the parameters of a neural network?
Re: Obstacles on the Path to AI
#16Earlier quoted context omitted.
He's saying you won't learn billions is parameters with RL /alone/ because "one scalar reward per trial isn't going to cut it". I find that convincing and a key insight. RL is going to be fundamental to AGI, but he's saying curiosity / unsupervised learning will be necessary. And I say this as a big believer in the need for more work on RL.
Yes, I should have added the context about the scalar reward, but I'm not sure why that changes anything. This may seem like a naive question, but it's sincere: What makes a scalar reward less effective at modifying a Q function than a scalar error that's used in backprop and assigned to a neural network's coefficients?
supervised learning: (after millions of operations you had just performed) out of 1000 you predicted label #136, but actually the true result for this input was label #25.
reinforcement learning: (after millions of operations you had just performed) out of 1000 you predicted label #136. That's not right, but I won't tell you what you should have done. Also, it could have been right, but maybe you had screwed up something in one of your last 100 predictions and I won't tell you what it was. Good luck.
Re: Obstacles on the Path to AI
#17Earlier quoted context omitted.
Yes, I should have added the context about the scalar reward, but I'm not sure why that changes anything. This may seem like a naive question, but it's sincere: What makes a scalar reward less effective at modifying a Q function than a scalar error that's used in backprop and assigned to a neural network's coefficients?
supervised learning: (after millions of operations you had just performed) out of 1000 you predicted label #136, but actually the true result for this input was label #25. reinforcement learning: (after millions of operations you had just performed) out of 1000 you predicted label #136. That's not right, but I won't tell you what you should have done. Also, it could have been right, but maybe you had screwed up somet…
that makes sense. thanks.
EDIT: followup question: to what extent does DeepMind's Deep-Q learning address the problem of associating remote causes with final outcomes?
Re: Obstacles on the Path to AI
#18Re: Obstacles on the Path to AI
#19Earlier quoted context omitted.
Yes, I should have added the context about the scalar reward, but I'm not sure why that changes anything. This may seem like a naive question, but it's sincere: What makes a scalar reward less effective at modifying a Q function than a scalar error that's used in backprop and assigned to a neural network's coefficients?
The point is that supervised training on large networks requires millions or billions of examples. In RL, that means potentially billions of execution trajectories, which can be really expensive if you're executing on an actual, physical robot. And even then, supervised classification objectives are more informative than just a scalar reward: when a supervised system makes a wrong prediction you don't just tell it "s…
It seems to me to be all about having the right prior and planning for exploration.
Policy search methods (http://arxiv.org/abs/1504.00702) assume that there aren't many trajectories that make sense (based on prior knowledge/testing in simulator) and search for the best ones among those that make sense using real-world data. Even within policy search you need some kind of exploration such injecting gaussian noise in trajectories. The hard part is to come up with a model for exploration.
Re: Obstacles on the Path to AI
#20Earlier quoted context omitted.
Yes, I should have added the context about the scalar reward, but I'm not sure why that changes anything. This may seem like a naive question, but it's sincere: What makes a scalar reward less effective at modifying a Q function than a scalar error that's used in backprop and assigned to a neural network's coefficients?
supervised learning: (after millions of operations you had just performed) out of 1000 you predicted label #136, but actually the true result for this input was label #25. reinforcement learning: (after millions of operations you had just performed) out of 1000 you predicted label #136. That's not right, but I won't tell you what you should have done. Also, it could have been right, but maybe you had screwed up somet…
To move the analogies into general intelligence, start with the example of Elon Musk (a top notch example of GI). What drives Elon Musk? In interviews he's said he wants to be useful. He's achieving that goal in a big way.
Take the moment he decided to build a rocket. It was after he had a difficult meeting to buy a russian missile. He quickly roughed out, from first principles, that he should be able to build one himself. The /drive/ to make that analysis was in pursuit of his goal (and required reinforcement learning).
But what lifelong process filled his brain with all the complex and nuanced information needed to rapidly draw that conclusion? His curiosity, aka unsupervised learning, which led him to learn so many things over the years that culminated in that moment.
For this reason, I might make the analogy that RL is the "conductor of the symphony", rather than calling it the "cherry on top" as LeCun does here.