update train.py

README.md

@@ -8,7 +8,9 @@ For detailed & latest documentation about the competition/template, see the orig
 This repository is a sample of the "Round 1" submission, i.e., the agents are trained locally.  
 
 `test.py` is the entrypoint script for Round 1.  
-Please ignore `train.py`, which will be used in Round 2.
+
+The `train.py`, which is the entrypoint for Round 2, have not been checked if it could work on the MineRL Competition's submission system yet.
+To train this baseline agent, see "How to Train Baseline Agent on your own" section below.
 
 `train/` directory contains baseline agent's model weight files trained on `MineRLObtainDiamondDenseVectorObf-v0`.
 

train.py

 # 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)
 
+import sys
+sys.path.append(os.path.abspath(os.path.join(__file__, os.pardir, 'mod')))
+from dqn_family import main as dqn_family_main
+
+
 # All the evaluations will be evaluated on MineRLObtainDiamond-v0 environment
-MINERL_GYM_ENV = os.getenv('MINERL_GYM_ENV', 'MineRLObtainDiamondVectorObf-v0')
+# MINERL_GYM_ENV = os.getenv('MINERL_GYM_ENV', 'MineRLObtainDiamondVectorObf-v0')
+MINERL_GYM_ENV = os.getenv('MINERL_GYM_ENV', 'MineRLObtainDiamondDenseVectorObf-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
@@ -40,39 +41,20 @@ parser = Parser('performance/',
 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
+    **IMPORTANT NOTICE**:
+    The trained weights in `train/` directory of this repository were generated by `mod/dqn_family.py::main` entry point,
+    not by this script.
+    I've not checked if this script (`train.py`) could work on the MineRL Competition's submission system.
+    (On the Round 1, participants are to submit pre-trained agents.
+    You have to make your training script work on the competition submission system on the Round 2.)
 
-#         # 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)
+    For the detail of the options of `dqn_family_main` called below, see "README#How to Train Baseline Agent on you own" section.
+    """
+    dqn_family_main()
 
-    # Save trained model to train/ directory
     # Training 100% Completed
     aicrowd_helper.register_progress(1)
-    #env.close()
 
 
 if __name__ == "__main__":