How can I reward an agent to move forward in a game like super Mario bros? The only data I have is the score and lives but is there a way to get the coordinates of an agent? I'm using NEAT to train my agent here is the code. I am currently rewarding it to get the highest score possible and rewarding it for pressing the Right button won't work because it will just push into a wall and farm rewards until the timer runs out.
import retro
import numpy as np
import cv2
import neat
import pickle
env = retro.make('SuperMarioWorld-Snes', 'Start.state')
imgarray = []
xpos_end = 0
def eval_genomes(genomes, config):
for genome_id, genome in genomes:
ob = env.reset()
ac = env.action_space.sample()
inx, iny, inc = env.observation_space.shape
inx = int(inx / 8)
iny = int(iny / 8)
net = neat.nn.recurrent.RecurrentNetwork.create(genome, config)
current_max_fitness = 0
fitness_current = 0
frame = 0
counter = 0
xpos = 0
xpos_max = 0
done = False
# cv2.namedWindow("main", cv2.WINDOW_NORMAL)
while not done:
env.render()
frame += 1
# scaledimg = cv2.cvtColor(ob, cv2.COLOR_BGR2RGB)
# scaledimg = cv2.resize(scaledimg, (iny, inx))
ob = cv2.resize(ob, (inx, iny))
ob = cv2.cvtColor(ob, cv2.COLOR_BGR2GRAY)
ob = np.reshape(ob, (inx, iny))
# cv2.imshow('main', scaledimg)
# cv2.waitKey(1)
imgarray = np.ndarray.flatten(ob)
nnOutput = net.activate(imgarray)
for i in range(len(nnOutput)):
nnOutput[i] = int(nnOutput[i])
if nnOutput[i] < 0:
nnOutput[i] = 0
ob, rew, done, info = env.step(nnOutput)
# xpos = info['x']
# xpos_end = info['screen_x_end']
# if xpos > xpos_max:
# fitness_current += 1
# xpos_max = xpos
# if xpos == xpos_end and xpos > 500:
# fitness_current += 100000
# done = True
fitness_current += rew
print(env.statename)
if fitness_current > current_max_fitness:
current_max_fitness = fitness_current
counter = 0
else:
counter += 1
if done or counter == 250:
done = True
print(genome_id, fitness_current)
genome.fitness = fitness_current
config = neat.Config(neat.DefaultGenome, neat.DefaultReproduction,
neat.DefaultSpeciesSet, neat.DefaultStagnation,
'config.txt')
p = neat.Population(config)
p.add_reporter(neat.StdOutReporter(True))
stats = neat.StatisticsReporter()
p.add_reporter(stats)
p.add_reporter(neat.Checkpointer(10))
winner = p.run(eval_genomes)
with open('winner.pkl', 'wb') as output:
pickle.dump(winner, output, 1)
Using print( retro.__file__ ) I found folder with module retro and checking all subfolders I found folder with SuperMarioWorld
On my Linux it is
/usr/local/lib/python3.8/dist-packages/retro/data/stable/SuperMarioWorld-Snes
There is file data.json which defines how retro has to find score and lives in ROM
In OpenAI-Retro-SuperMarioWorld-SNES I found data.json which has also info for x, y, etc.
If I replace data.json then I can get info["x"] in code .
But I'm not sure if this file works with every version of SuperMario.
I tested with Super Mario World (Europe) (Rev 1) which I found on
but there are other versions - Europe, USA, Japan.