A rocket league agent has naturally 3 continuous and 5 multi-discrete actions. Being able to represent this structure in our model may be beneficial for the agent's performance. The environment team implemented a gym unity wrapper, which supports mixed actions spaces (the wrapper of ml-agents does not support this feature). With this wrapper we can test, whether MSF supports mixed action spaces and whether we get any performance boost out of it.
Tasks
[x] Add mixed action space environment to the MSF env registry (happend in main branch)
[x] Copy gym unity wrapper of the environment team into MSF (from here on branch iss25 is used)
[x] Extend transform_action_space method for tuples with multidiscrete action spaces inside
General Description
A rocket league agent has naturally 3 continuous and 5 multi-discrete actions. Being able to represent this structure in our model may be beneficial for the agent's performance. The environment team implemented a gym unity wrapper, which supports mixed actions spaces (the wrapper of ml-agents does not support this feature). With this wrapper we can test, whether MSF supports mixed action spaces and whether we get any performance boost out of it.
Tasks