[Question] Why is the default discount factor 0.999 for PPO and 0.99 for DQN?

RLE-Foundation / rllte

Long-Term Evolution Project of Reinforcement Learning

https://docs.rllte.dev/

MIT License

453 stars 84 forks source link

Open roger-creus opened 8 months ago

roger-creus commented 8 months ago

I would think 0.99 is the most widely used default value, so I suggest using that for PPO as well.

[X] I have checked that there is no similar issue in the repo
[X] I have read the documentation
[X] If code there is, it is minimal and working
[X] If code there is, it is formatted using the markdown code blocks for both code and stack traces.

yuanmingqi commented 8 months ago

0.999 is used for the Procgen games.