while (X < 5600)
{
Console.WriteLine("-20 4");
while ( Y < 590)
{
Console.WriteLine("0 4");
}
}
Basicly once the space ship reaches a section of the mars it will start to counter
the gravity and stuff but once all that works the while loop inside the while loop that supposed to initiate once the spaceship is near the ground to land wont run why?
Also yes I am a noob :> I did not finish the second one but i just wanted to see what the 3rd episode looked like
The variables X and Y wonât update themselves. If you need updated values of the position, you have to read the inputs again and update those variables after your Console.WriteLine.
After 1 month trial, I finally pass Level3 with reinforcement learning approach!
my steps:
write a simulator, modified base on âgymnasiumâ LunarLander env
mainly learn Box2d to simulate physical movement and detect collision
design action space: since the space is large, I reduce the action to 3x2 (+15/0/-15 for rotate with clip of ±45degree, +1/-1 for power with clip of 0-4)
train a policy with help of âstable baseline3â PPO model
tried DQN first, then switch to PPO
need to carefully design the input and the reward function
input: in final version, I give a 13 dimension vector as input [distance in 6 directions, h/v speed, rotate, power, relative h/v distance to the middle of landing zone, whether the lander can see the LandingZone]. normalize with modified sigmoid function to get all input in range [-1,1].
reward: lots of pains in reward function design, +++ for success landing, + for approaching (i use the angle leftOfLandingZone-rocket-rightOfLandingZone as a indicator), â for collision, - for too high speed, - for high power, â for wrong direction
training: since the space is very large, I train gradually (at beginning, the rocket start very near to the LandingZone, to get a good Q-value/Policy for that area, then gradually move the start far away and eventually the actual start point). I use random map between the 2 tests and random starting point (with randomness on position(with in the chosen area)/speed/rotationâŠ) in âmake_vec_envâ to train.
network arch: first I used a 4x200 nodes policy network and a same form of vf network, but then find out the parameters are too big for the 100k code limit.
in final version is 2x100 nodes policy network and 4x200 vf network.
transfer the parameters (tensor or numpy array to base64 string) and use in codingame.
thanks to the help from @ jacek1 and @ FrancoisB about this part :))) (the Unicode method is genius, but since I reduce my network, I wonât need that magic this time)
manually calculate the âpredictionâ part to get output from neural network
Hello everyone,
When I did this puzzle, I wrote a program that allowed me to run my solution locally and draw on the visualization. This allowed me to see the trajectories I was simulating and it helped me a lot.
So I wanted to share my program with you, in case it might help you too.
