Attempting to replicate "A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem" https://arxiv.org/abs/1706.10059 (and an openai gym environment)
Firstly wassname, thank you so much for sharing this excellent piece of work! It has been extremely interesting to work on, and particularly opened my eyes to universal portfolios. Secondly, I have a question about what random_reset does in PortfolioEnv? I cannot use my adapted environment from your work without raising loads of errors. I'd be very grateful if you could clarify the differences in random_reset=False and random_reset=True.
Firstly wassname, thank you so much for sharing this excellent piece of work! It has been extremely interesting to work on, and particularly opened my eyes to universal portfolios. Secondly, I have a question about what random_reset does in PortfolioEnv? I cannot use my adapted environment from your work without raising loads of errors. I'd be very grateful if you could clarify the differences in random_reset=False and random_reset=True.
Thanks! Stewart