ReinforcementLearning | Reinforcing Your Learning of Reinforcement | Reinforcement Learning library

I am trying to create a simultaneous multi agent environment using reinforcementlearning.jl
I have successfully represented the environment and it works with a RandomPolicy for every agent.

But my state space is large (actually it's a 14 tuple with each value in a certain range). So I can not use Tabular Approximators to estimate the Q or V values. That's why I have decided to use a Neural Network Approximator. But the docs do not discuss much about it, nor are there any examples were neural network approximator is used. I am stuck how to figure out how to use such approximator. If anyone can explain how to go about it, or refer to any example, it would be helpful.

Moreover I found from docs that using a Neural Network approximator needs us to use a CircularArraySARTTrajectory. But defining this trajectory requires a key word argument called capacity. I don't know what it means, nor it is discussed about in the docs and GitHub.

I tried writing the code that uses neural network approximator but I get error.

I have been learning Reinforcement Learning for few days now, and I have seen example problems like Mountain Car problem and Cart Pole problem.

In these problems, the way action space is described is discrete. For example in Cart Pole Problem, the agent can either move left or move right.

1. But the examples don't talk about how much? How does the agent decide how much to move left, how much to move right, after all these movements are continuous space actions. So I want to know how does the agent decide what real value to choose from a continuous action space.

2. Also I have been using ReinforcementLearning.jl in Julia and wanted to know a way i could represent range constraints on action space in it. Example, the real value that the agent chooses as it's action should lie in a range like [10.00, 20.00[ for example. I want to know how this can be done.

I am following this tutorial on Policy Gradient using Keras, and can't quite figure out the below.

In the below case, how exactly are input tensors with different shapes fed to the model?
Layers are neither .concated or .Added.

• input1.shape = (4, 4)
• input2.shape = (4,)
• "input" layer has 4 neurons, and accepts input1 + input2 as 4d vector??

The code excerpt (modified to make it simpler) :

I am working with Cython to speed up some python code and I am running into the following error:

I am following this online tutorial for coding a DQN,https://github.com/philtabor/Youtube-Code-Repository/blob/master/ReinforcementLearning/DeepQLearning/torch_deep_q_model.py , however I am running into this Runtime Error that I am unsure of how to debug or modify to prevent this error. Thanks!