I’m working at a Reinforcement Learning model, using PPO algorithm, in which the agent has 4 possible actions, acting in a stochastic environment defined by 3 parameters. Given its stochasticity, I was thinking it would be better to store also the parameters of the previous step, ending up in 6 parameters. My question is: when these parameters are too many? If I store the previous 5 results, I end up with 5*3=15 parameters, thus it could be more...
Originally asked by Damuna Taliffato on Stack Exchange (ai) (CC BY-SA 4.0).
