Closed saiyuhang123 closed 2 months ago
I have made a multi-agent pathfinding in a grid world. The state adopts the Manhattan distance between the agent and the goal. Does it need to be normalized when inputting the state information to mappo?
Generally you don‘t need to do normalization by yourself since we will do valuenorm when processing the observation in the policy network.
I have made a multi-agent pathfinding in a grid world. The state adopts the Manhattan distance between the agent and the goal. Does it need to be normalized when inputting the state information to mappo?