Question about whether need to train multiple agents for different games

[QiGuLongDongQiang]

Thanks for you open-sourced code very much. Recently, I want to apply the model used for breakout to other games, but I find that different games have different action Spaces, which will lead to errors in the process of test, the parameter dimension of breakout is inconsistent with that of other games, I would like to ask whether each game needs to train an agent separately,I really hope to get your answer,tank you

[YeWR]

Each game needs to train an agent separately.

The dynamics function takes in the actions, and the policy function outputs the actions. Since different environments have different actions and the current agent interacts with one environment at a time, the trained Breakout model cannot transfer to another environment.