def test_next_policy_action(self): bot = BotSimpleRL(self.env, self.player) bot.init_q_state(0) assert bot.next_policy_action(bot.dehasher(0), 0) == -1 pass
def test_init_q_state(self): bot = BotSimpleRL(self.env, self.player) bot.init_q_state(0) assert len(bot.q_table[0]) == len(self.player.actions(self.env.dehasher(0))) for each in bot.q_table[0]: assert each == self.env.q_init