Disclaimer: Dieser Thread wurde aus dem alten Forum importiert. Daher werden eventuell nicht alle Formatierungen richtig angezeigt. Der ursprüngliche Thread beginnt im zweiten Post dieses Threads.

Dear SAKI-Team,

I have trouble understanding exercise 3. Please can you explain to me in terms of reinforcement learning?

  • what is the final goal?

  • how can we more simply define our environment (States (and S0) ?, Actions?, Transition_function ?, Rewards?)?

  • what is the role of experts in all this?

  • what other information can allow me to understand the objective and the environment of the trader easily?

big thanks!!!

(I don’t know anything about trading unfortunately)

I guess you are working on 2019 homework? This semester’s homework will be presented this week.