Inital commit

README.md

@@ -0,0 +1,149 @@
+![AIcrowd-Logo](https://raw.githubusercontent.com/AIcrowd/AIcrowd/master/app/assets/images/misc/aicrowd-horizontal.png)
+
+# NeurIPS 2019 : MineRL Challenge Starter Kit
+
+Instructions to make submissions to the [NeurIPS 2019 : MineRL Challenge](https://www.aicrowd.com/challenges/neurips-2019-minerl-competition).
+
+Participants will have to submit their code, with packaging specifications, and the evaluator will automatically build a docker image and execute their code against a series of secret datasets.
+
+![](https://i.imgur.com/XB1WORT.gif)
+
+### Setup
+
+- **Anaconda** (By following instructions [here](https://www.anaconda.com/download)) At least version `4.5.11` is required to correctly populate `environment.yml`.
+
+* **Create your new conda environment**
+
+```sh
+conda create --name minerl_challenge
+conda activate minerl_challenge
+```
+
+* **Your code specific dependencies**
+
+```sh
+conda install <your-package>
+```
+
+### Clone repository
+
+```
+git clone git@github.com:AIcrowd/neurips2019_minerl_challenge_starter_kit.git
+cd neurips2019_minerl_challenge_starter_kit
+pip install -r requirements.txt
+```
+
+### Your Submission
+
+To get started with the environment and dataset [please check out our quick start guide here](http://minerl.io/docs/tutorials/getting_started.html)!
+
+This competition uses a set of Gym environments based on [Malmo](https://github.com/Microsoft/malmo). The environment and dataset loader will be available through a pip package.
+
+The main task of the competition is solving the `ObtainDiamond` environment. In this environment, the agent begins in a random starting location without any items, and is tasked with obtaining a diamond. This task can only be accomplished by navigating the complex item hierarchy of Minecraft.
+
+
+# How do I specify my software runtime ?
+
+The software runtime is specified by exporting your `conda` env to the root
+of your repository by doing :
+
+```
+conda env export --no-build > environment.yml
+
+# It might make sense here to remove the requirements.txt here to avoid confusion as environment.yml takes precedence over requirements.txt
+```
+
+This `environment.yml` file will be used to recreate the `conda environment`. This repository includes an example `environment.yml`
+
+# What should my code structure be like ?
+
+Please follow the structure documented in the included [agent.py](https://github.com/AIcrowd/neurips2019_minerl_challenge_starter_kit/blob/master/agent.py) to adapt
+the required structure for this round.
+
+## Important Concepts
+
+### Repository Structure
+
+- `aicrowd.json`
+  Each repository should have a `aicrowd.json` with the following content :
+
+```json
+{
+  "challenge_id": "aicrowd-neurips-2019-minerl-challenge",
+  "grader_id": "aicrowd-neurips-2019-minerl-challenge",
+  "authors": ["your-aicrowd-username"],
+  "description": "sample description about your awesome agent",
+  "license": "MIT",
+  "gpu": true
+}
+```
+
+This is used to map your submission to the said challenge, so please remember to use the correct `challenge_id` and `grader_id` as specified above.
+
+Please specify if your code will a GPU or not for the evaluation of your model. If you specify `true` for the GPU, a **NVIDIA Tesla K80 GPU** will be provided and used for the evaluation.
+
+### Packaging of your software environment
+
+The recommended way is to use Anaconda configuration files using **environment.yml** files.
+
+```sh
+# The included environment.yml is generated by the command below, and you do not need to run it again
+# if you did not add any custom dependencies
+
+conda env export --no-build > environment.yml
+
+# Note the `--no-build` flag, which is important if you want your anaconda env to be replicable across all
+# Or if you have a rather simple softwar runtime, then even a :
+#
+# pip freeze > requirements.txt
+#
+# could work.
+```
+
+### Code Entrypoint
+
+The evaluator will use `/home/aicrowd/run.sh` as the entrypoint, so please remember to have a `run.sh` at the root, which can instantitate any necessary environment variables, and also start executing your actual code. This repository includes a sample `run.sh` file.
+If you are using a Dockerfile to specify your software environment, please remember to create a `aicrowd` user, and place the entrypoint code at `run.sh`.
+
+## Submission
+
+To make a submission, you will have to create a private repository on [https://gitlab.aicrowd.com/](https://gitlab.aicrowd.com/).
+
+You will have to add your SSH Keys to your GitLab account by following the instructions [here](https://docs.gitlab.com/ee/gitlab-basics/create-your-ssh-keys.html).
+If you do not have SSH Keys, you will first need to [generate one](https://docs.gitlab.com/ee/ssh/README.html#generating-a-new-ssh-key-pair).
+
+Then you can create a submission by making a _tag push_ to your repository on [https://gitlab.aicrowd.com/](https://gitlab.aicrowd.com/).
+**Any tag push (where the tag name begins with "submission-") to your private repository is considered as a submission**  
+Then you can add the correct git remote, and finally submit by doing :
+
+```
+cd neurips2019_minerl_challenge_starter_kit
+# Add AIcrowd git remote endpoint
+git remote add aicrowd git@gitlab.aicrowd.com:<YOUR_AICROWD_USER_NAME>/neurips2019_minerl_challenge_starter_kit.git
+git push aicrowd master
+
+# Create a tag for your submission and push
+git tag -am "submission-v0.1" submission-v0.1
+git push aicrowd master
+git push aicrowd submission-v0.1
+
+# Note : If the contents of your repository (latest commit hash) does not change,
+# then pushing a new tag will **not** trigger a new evaluation.
+```
+
+You now should be able to see the details of your submission at :
+[gitlab.aicrowd.com/<YOUR_AICROWD_USER_NAME>/neurips2019_minerl_challenge_starter_kit/issues](gitlab.aicrowd.com//<YOUR_AICROWD_USER_NAME>/neurips2019_minerl_challenge_starter_kit/issues)
+
+**NOTE**: Remember to update your username in the link above :wink:
+
+In the link above, you should start seeing something like this take shape (each of the steps can take a bit of time, so please be patient too :wink: ) :
+![](https://i.imgur.com/FqScw4m.png)
+
+and if everything works out correctly, then you should be able to see the final scores like this :
+![](https://i.imgur.com/u00qcif.png)
+
+**Best of Luck** :tada: :tada:
+
+# Author
+
+Shivam Khandelwal <https://twitter.com/skbly7>

agent.py

@@ -0,0 +1,56 @@
+# Simple env test.
+import json
+import select
+import time
+import logging
+
+import gym
+import matplotlib.pyplot as plt
+import minerl
+import numpy as np
+from minerl.env.core import MineRLEnv
+
+import coloredlogs
+coloredlogs.install(logging.DEBUG)
+
+
+#import minerl.env.bootstrap
+#minerl.env.bootstrap._check_port_avail = lambda _,__: True
+
+NUM_EPISODES = int(os.getenv('MINERL_NUM_EPISODES', 1))
+MINERL_GYM_ENV = os.getenv('MINERL_GYM_ENV', 'MineRLNavigateDense-v0')
+
+def main():
+    """
+    Tests running a simple environment.
+    """
+    env = gym.make(MINERL_GYM_ENV)
+
+    actions = [env.action_space.sample() for _ in range(2000)]
+    xposes = []
+    for _ in range(NUM_EPISODES):
+        obs, info = env.reset()
+        done = False
+        netr = 0
+        while not done:
+            random_act = env.action_space.noop()
+
+            random_act['camera'] = [0, 0.1*obs["compassAngle"]]
+            random_act['back'] = 0
+            random_act['forward'] = 1
+            random_act['jump'] = 1
+            random_act['attack'] = 1
+            # print(random_act)
+            obs, reward, done, info = env.step(
+                random_act)
+            # print(obs["compassAngle"])
+            netr += reward
+            print(reward, netr)
+            env.render()
+
+
+
+    print("Demo complete.")
+
+if __name__ == "__main__":
+    main()

aicrowd.json

@@ -0,0 +1,7 @@
+{
+  "challenge_id": "aicrowd-neurips-2019-minerl-challenge",
+  "grader_id": "aicrowd-neurips-2019-minerl-challenge",
+  "authors": ["aicrowd-bot"],
+  "description": "Test Model for MineRL Challenge",
+  "gpu": false
+}

apt.txt

@@ -0,0 +1,14 @@
+curl
+git
+vim
+ssh
+gcc
+python-dev
+libsm6
+libxext6
+libxrender-dev
+libglib2.0-0
+openjdk-8-jdk
+xvfb
+x11vnc
+freeglut3-dev

debug_build.sh

@@ -0,0 +1,21 @@
+#!/bin/bash
+
+
+if [ -e environ_secret.sh ]
+then
+    source environ_secret.sh
+else
+    source environ.sh
+fi
+
+# Expected Env variables : in environ.sh
+
+REPO2DOCKER="$(which aicrowd-repo2docker)"
+
+sudo ${REPO2DOCKER} --no-run \
+  --user-id 1001 \
+  --user-name aicrowd \
+  --image-name ${IMAGE_NAME}:${IMAGE_TAG} \
+  --debug .
+
+#sudo docker push "${IMAGE_NAME}:${IMAGE_TAG}"

docker_run.sh

@@ -0,0 +1,23 @@
+#!/bin/bash
+
+
+if [ -e environ_secret.sh ]
+then
+    echo "Note: Gathering environment variables from environ_secret.sh"
+    source environ_secret.sh
+else
+    echo "Note: Gathering environment variables from environ.sh"
+    source environ.sh
+fi
+
+# Expected Env variables : in environ.sh
+sudo nvidia-docker run \
+    --net=host \
+    -v $(pwd)/../gradle-data-init/downloads:/home/aicrowd/.gradle:z \
+    -v /tmp/shared:/shared:z \
+    --user 0 \
+    -e CROWDAI_IS_GRADING=True \
+    -e CROWDAI_DEBUG_MODE=True \
+    -it ${IMAGE_NAME}:${IMAGE_TAG} \
+    xvfb-run --auto-servernum --server-args='-screen 0 640x480x24' \
+    /home/aicrowd/run.sh

environ.sh

@@ -0,0 +1,8 @@
+#!/bin/bash
+
+
+# debug_build.sh
+export IMAGE_NAME="aicrowd/neurips2019-minerl-challenge"
+export IMAGE_TAG="agent"
+
+# docker_run.sh

requirements.txt

@@ -0,0 +1,5 @@
+crowdai_api
+minerl==0.1.18
+coloredlogs
+matplotlib
+opencv-python

run.sh

@@ -0,0 +1,2 @@
+#!/bin/bash
+python ./agent.py