train.py 3.54 KB
Newer Older
pfrl_rainbow's avatar
pfrl_rainbow committed
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79
# Simple env test.
import json
import select
import time
import logging
import os

import aicrowd_helper
import gym
import minerl
from utility.parser import Parser

import coloredlogs
coloredlogs.install(logging.DEBUG)

# All the evaluations will be evaluated on MineRLObtainDiamond-v0 environment
MINERL_GYM_ENV = os.getenv('MINERL_GYM_ENV', 'MineRLObtainDiamondVectorObf-v0')
# You need to ensure that your submission is trained in under MINERL_TRAINING_MAX_STEPS steps
MINERL_TRAINING_MAX_STEPS = int(os.getenv('MINERL_TRAINING_MAX_STEPS', 8000000))
# You need to ensure that your submission is trained by launching less than MINERL_TRAINING_MAX_INSTANCES instances
MINERL_TRAINING_MAX_INSTANCES = int(os.getenv('MINERL_TRAINING_MAX_INSTANCES', 5))
# You need to ensure that your submission is trained within allowed training time.
# Round 1: Training timeout is 15 minutes
# Round 2: Training timeout is 4 days
MINERL_TRAINING_TIMEOUT = int(os.getenv('MINERL_TRAINING_TIMEOUT_MINUTES', 4*24*60))
# The dataset is available in data/ directory from repository root.
MINERL_DATA_ROOT = os.getenv('MINERL_DATA_ROOT', 'data/')

# Optional: You can view best effort status of your instances with the help of parser.py
# This will give you current state like number of steps completed, instances launched and so on. Make your you keep a tap on the numbers to avoid breaching any limits.
parser = Parser('performance/',
                allowed_environment=MINERL_GYM_ENV,
                maximum_instances=MINERL_TRAINING_MAX_INSTANCES,
                maximum_steps=MINERL_TRAINING_MAX_STEPS,
                raise_on_error=False,
                no_entry_poll_timeout=600,
                submission_timeout=MINERL_TRAINING_TIMEOUT*60,
                initial_poll_timeout=600)

def main():
    """
    This function will be called for training phase.
    """
    # How to sample minerl data is document here:
    # http://minerl.io/docs/tutorials/data_sampling.html
    data = minerl.data.make(MINERL_GYM_ENV, data_dir=MINERL_DATA_ROOT)

    # Sample code for illustration, add your training code below
    env = gym.make(MINERL_GYM_ENV)

#     actions = [env.action_space.sample() for _ in range(10)] # Just doing 10 samples in this example
#     xposes = []
#     for _ in range(1):
#         obs = env.reset()
#         done = False
#         netr = 0

#         # Limiting our code to 1024 steps in this example, you can do "while not done" to run till end
#         while not done:

            # To get better view in your training phase, it is suggested
            # to register progress continuously, example when 54% completed
            # aicrowd_helper.register_progress(0.54)

            # To fetch latest information from instance manager, you can run below when you want to know the state
            #>> parser.update_information()
            #>> print(parser.payload)
            # .payload: provide AIcrowd generated json
            # Example: {'state': 'RUNNING', 'score': {'score': 0.0, 'score_secondary': 0.0}, 'instances': {'1': {'totalNumberSteps': 2001, 'totalNumberEpisodes': 0, 'currentEnvironment': 'MineRLObtainDiamond-v0', 'state': 'IN_PROGRESS', 'episodes': [{'numTicks': 2001, 'environment': 'MineRLObtainDiamond-v0', 'rewards': 0.0, 'state': 'IN_PROGRESS'}], 'score': {'score': 0.0, 'score_secondary': 0.0}}}}
            # .current_state: provide indepth state information avaiable as dictionary (key: instance id)

    # Save trained model to train/ directory
    # Training 100% Completed
    aicrowd_helper.register_progress(1)
    #env.close()


if __name__ == "__main__":
    main()