Michael Jacob

maybe a little late, but 181 is the dimension of the state space: balance + num_stocks+holdings +technichal indiactors 1+30+30+4*30 (4 technical indicators for each 30 stocks) = 181 balance =...

you could mofiy the environment and create an environment to track at each time stemp the weights and output it as a csv after testing the agent and analyse the...

From my point of view buy and sell actions are ranked according to the ammount to buy at each time step. So you are right if you have 3000 stocks...

self.cost is a is a variable to track the cost of the agents strategy and updated after each sell/buy action += it will change the account balance because the cost...