M-J-Murray
How to you see the learning data that is graphed in the Readme?
Simple ConvNet Agent: How to you see the ML data that is graphed in the Readme?
Once I hit escape key I do not see any data?
I expect to see reward vs games.
Thanks,
Rick
script:
#!/usr/bin/env python3
import random from MAMEToolkit.sf_environment import Environment
roms_path = "roms/" # Replace this with the path to your ROMs env = Environment("env1", roms_path) env.start() #while True: move_action = random.randint(0, 8) attack_action = random.randint(0, 9) frames, reward, round_done, stage_done, game_done = env.step(move_action, attack_action) if game_done: env.new_game() elif stage_done: env.next_stage() elif round_done: env.next_round()
If I just hit escape I see:
parallels@parallels-Parallels-Virtual-Platform:~$ python3.6 ./sf.py Failed to read value from 'dataPipe' Traceback (most recent call last): File "/home/parallels/.local/lib/python3.6/site-packages/MAMEToolkit/emulator/pipes/Pipe.py", line 96, in readln return self.read_queue.get(timeout=timeout) File "/usr/lib/python3.6/queue.py", line 172, in get raise Empty queue.Empty
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "./sf.py", line 13, in
The toolkit does not automatically create the graph. If you want to build this graph you will need to take the sum or rewards for every episode. Then you can use the Matplotlib library to build the graph. It's fairly simple to use. Best of luck!
Also each time you start the emulator does the alg start from ground zero each time?
The toolkit does not keep track of overall stats across an episode. You will need to store every reward returned from the step function over an entire episode yourself.