So finding Lean proofs can be conceptualized as a zero-sum game?
Another basic requirement is that valid moves / inference steps and the winning condition can be efficiently verified using some non-AI algorithm. Otherwise there would not be a reward signal for the reinforcement learning algorithm. This is different from answering most natural language questions, where the answer can't be checked trivially.
Another basic requirement is that valid moves / inference steps and the winning condition can be efficiently verified using some non-AI algorithm. Otherwise there would not be a reward signal for the reinforcement learning algorithm. This is different from answering most natural language questions, where the answer can't be checked trivially.