Question 1: Short answer
easyAI-checkedRL FundamentalsA Connect Four agent gets a reward after each of its moves: +1 if the move wins, −10 if the move is invalid (which ends the game), −1 if the opponent wins on its next move, and otherwise. In one game the agent moves first, plays 7 times and wins with its 7th move. What is its cumulative reward? Round to 3 decimals.