This is a highly relevant question as market trends have become more emphasized over the fundamentals of individual companies, and algorithmic trading has proven to be quite effective, particularly in areas such as high-frequency micro-trading.
This 2013 Forbes article estimated nearly 80% of stock trading volume in the U.S. is conducted by automated ...
I recommend you read up on reinforcement learning. Seeing how AirHockey is similar to the old Atari game Pong, here is a write-up (with code) about how to implement a simple neural network, that plays the game; Deep Reinforcement Learning: Pong from Pixels.
As far as the choice of layers go, again, you should read up on deep reinforcement learning, perhaps ...
A couple of thoughts:
Humans can't reliably predict trends in the stock market, so expecting AI's to do so is probably unreasonable.
The above would be more true if it were proven that the movement of stock prices is really a random walk, but my understanding is that the current thinking is that stock movements aren't completely random... but just really ...
I have been looking for a while into pretty much precisely the problem you describe (including the same application domain), but haven't been able to find much.
The most obvious, mathematically "correct" solution would be to simply delay your standard Reinforcement Learning update rule (of whatever algorithm you choose to implement) by 45 days; if it still ...
We are getting there, with as usual some trade-off between quality and speed.
For example Lecture 8: Spatial Localization and Detection lecture shows some benchmarks (mAP = Mean Average Precision, higher is better; FPS = frame per second):
First you'd need to mathematically model your real environment. Probably use some differential equations.
Once you have a good model, you still won't have your real case parameters. So I can see 2 different approaches:
Theoretically + Experimentally: Empirically measure real data to try to find those parameters. (Make a simple PID controller)
Make a robust ...
Short answer: Yes, it is.
Reinforcement learning can be considered as a online learning. That is, you can train your model with a single data/reward pairs. As with any online learning algorithm, there are a few things to consider.
The model tends to forget the knowledge gained. To overcome this problem, one can save new data in a circular ...
OK, here is one approach.
Acquire a data set of 'clean' audio samples without barking dogs and an data set of barking dogs sounds.
Generate a training set by mixing random selections of clean audio with a random selections of barking dog noises at various volume levels. This is your input data. Your output data is the clean audio before you added the ...
There is quite some research done by Hans-Georg Zimmermann, who has programmed Neural Networks for Siemens since some 20 years in order to predict Stock markets. He wrote some books on it, too, though I don't know if they are any good in English.
This article gets to the point a bit faster than the video, I hope it helps.
edit: I think this interview gives ...
About 15 years ago, John Laird's group at Michigan used the Soar rule-based architecture to play several FPS games effectively (Quake II, Descent III):
Here's Laird's overview article from 'Computer':
An agent perceives the environment through sensors and act according to the incoming percepts (agent's perceptual input at any instant). An autonomous vacuum cleaner can be as simple as
(blocki, clean) --> Move to blocki+1
(blocki, dirty) --> Clean
This is just a general description, actual one is more complicated. Or the bot can have a memory where it ...
Most of the algorithms (based on image synthesis and style transfer, e.g. neural-doodle) haven't been proven to be highly effective in terms of real-time image processing.
However the following studies discusses such algorithms for real-time texture synthesis:
Feed-forward Synthesis of Textures and Stylized Images
The approach is to move the computational ...