# Tag Info

6

Why has this merge proven beneficial? If you think about the shared Value/Policy network as consisting of a shared component (the Residual Network layers) with a Value and Policy component on top rather than Separation of Concerns it makes more sense. The underlying premise is that the shared part of the network (the ResNet) provides a high-level ...

4

I don't think that's necessarily a strange number. It's impossible for anyone to really tell you whether that 17% is "correct" or not without reproducing it, which would require much more info (basically would have to know every single tiny detail of your implementation to be able to reproduce). Some things to consider: The size of your transposition table ...

3

This partly answer to question 1. There is no general rule concerning accuracy or size of the model. It depends on the training data and the processed data. The lightest is your model compared to the full accuracy model the less accurate it will be. I would run the lite model on test data and compare to the accuracy of the full model to get an exact measure ...

3

The programmer already guides the RL algorithm (or agent) by specifying the reward function. However, the reward function alone may not be sufficient to learn efficiently and fast, as you correctly noticed. To attempt to solve this inefficiency problem, one solution is to combine reinforcement learning with supervised learning. For example, the paper Deep Q-...

2

There is some recent work addressing this issue, to learn the conditional probability of an output sequence with elements that are discrete tokens corresponding to positions in an input sequence. See Pointer Networks.

2

To the best of my knowledge, there isn't any difference between the algorithmic methods and the NN methods. Those that can solve in polynomial time do not give a precise solution. Those that do give a precise solution do not solve in polynomial time. Of those that give a precise solution, the fastest takes $2^N$, but it blows up in terms of memory. The ...

2

Here are two very related interesting papers: Learning from Human Preferences Improving Reinforcement Learning with Human Input

1

I'll use notation from the paper you cited, and any other readers should refer to the paper (widely available) for definitions of notation. The utility of using $W^Q$ and $W^K$, rather than $W$, lies in the fact that they allow us to add fewer parameters to our architecture. $W$ has dimension $d_{model} \times d_{model}$, which means that we are adding \$d_{...

1

AI can transform the customer experience is by providing personalized content. For example, When you see video recommendation on YouTube, you'll know that it's from AI technology. I recommend you to read this article for knowing how they work: A Sentiment-Enhanced Hybrid Recommender System for Movie Recommendation: A Big Data Analytics Framework (abstract, ...

1

This sounds to me like a use case for a chatbot. You would have different intents reflecting the types of user queries that your system can respond to. The intent matching can be done by pattern matching, machine learning (classification), or a combination of the two (hybrid). You can then use the chatbot to ask clarification questions or elicit more ...

1

There are several informed and uninformed search algorithms. They do not all have the same time and space complexity (which also depends on the specific implementation). I could come up with an informed search algorithm that is highly inefficient in terms of time or space complexity. So, in general, informed search algorithm are not more efficient than ...

1

It sounds like you're looking at the Partition Problem. https://en.wikipedia.org/wiki/Partition_problem The task of slicing one set into N sets so that each set is equal or as close to equal as possible. Obtaining an exact solution is NP-hard (you can't do much better than trying all combinations), however you can get an approximate answer in polynomial ...

1

My understanding of efficiency in this context is in regards to optimization of algorithms as opposed to hardware speed, which is more of a "brute force" component. GPUs may be more energy efficient, but this is distinct from linear optimization of algorithms. In terms of how much processor speed you need to tackle a given problem, that's in the realm of ...

Only top voted, non community-wiki answers of a minimum length are eligible