Open shao-wang-me opened 6 years ago
Unfortunately this is not supported by HFO. It may be possible to engineer this capability into the underlying rcssserver (https://github.com/mhauskn/rcssserver) but I suspect it would not be easy.
Thank you very much for replying. We found it difficult indeed. We initially tried to deep copy HFOEnvironment
objects in our Python agent...
Is it possible to start the game from a given state?
We are trying to run simulations for Monte Carlo Tree Search in HFO, but it seems that the environment does not support something like a transition function s' = t(s, a), or start the game from a given state.
Is there any way to do the simulation? Thanks!