I asked a question relating to TicTacToe playing in RL. From the answer it seems to me a lot is dependent on the opponent (rightly so, if we write down the Expectation Equations). My question is (in the context of TicTacToe or Chess):
- How to make the RL player a perfect player (TicTactoe) or an expert (chess). As far as TTT is concerned when playing against a perfect player an RL will become perfect conditioned on the clause that the opponent is perfect. So will this hold true if the same RL algo, with its learned values are used to play some other lesser perfect players?
- The question can be extended to the scenario, can a RL player with pre-trained values (assume from a perfect or expert opponent) be used in any scenario with best results?
Note: The problem is more severe in chess, since experts will use some kind of opening moves which will not match with say a random player and thus finding values for those states becomes a problem, since we have not encountered it during training time.
Footnote: Any resources on Game Playing RL is appreciated.