jacy

hi @daochenzha, is it just to use the random model to train?

ahh ok, seems it might still need to take lots of effort to train it reach to a normal human level

have been training mahjong game using DMC, seems the rewards didn't improve even train for several days, anyone can shed some light?

found the root cause: in mahjong extract_state function the raw_legal_actions and legal_actions doesn't match, legal_actions is the unique list of player's hand, but raw_legal_actions is the list of player's hand