README.md 4.47 KB
Newer Older
pfrl_rainbow's avatar
pfrl_rainbow committed
1
# NeurIPS 2020: MineRL Competition Rainbow Baseline with PFRL
pfrl_rainbow's avatar
pfrl_rainbow committed
2

pfrl_rainbow's avatar
pfrl_rainbow committed
3
4
This repository is a **Rainbow baseline submission example with [PFRL](https://github.com/pfnet/pfrl)**,
originated from [the main MineRL Competition submission template and starter kit](https://github.com/minerllabs/competition_submission_template).
pfrl_rainbow's avatar
pfrl_rainbow committed
5

pfrl_rainbow's avatar
pfrl_rainbow committed
6
For detailed & latest documentation about the competition/template, see the original template repository.
pfrl_rainbow's avatar
pfrl_rainbow committed
7

pfrl_rainbow's avatar
pfrl_rainbow committed
8
This repository is a sample of the "Round 1" submission, i.e., the agents are trained locally.  
pfrl_rainbow's avatar
pfrl_rainbow committed
9

pfrl_rainbow's avatar
pfrl_rainbow committed
10
11
`test.py` is the entrypoint script for Round 1.  
Please ignore `train.py`, which will be used in Round 2.
pfrl_rainbow's avatar
pfrl_rainbow committed
12

pfrl_rainbow's avatar
pfrl_rainbow committed
13
`train/` directory contains baseline agent's model weight files trained on `MineRLObtainDiamondDenseVectorObf-v0`.
pfrl_rainbow's avatar
pfrl_rainbow committed
14

pfrl_rainbow's avatar
pfrl_rainbow committed
15
16
17
## List of current baselines
- [Rainbow](https://github.com/keisuke-nakata/minerl2020_submission) <-- We are here
- [SQIL](https://github.com/s-shiroshita/minerl2020_sqil_submission)
pfrl_rainbow's avatar
pfrl_rainbow committed
18

pfrl_rainbow's avatar
pfrl_rainbow committed
19
# How to Submit
pfrl_rainbow's avatar
pfrl_rainbow committed
20

pfrl_rainbow's avatar
pfrl_rainbow committed
21
22
23
After [signing up the competition](https://www.aicrowd.com/challenges/neurips-2020-minerl-competition), specify your account data in `aicrowd.json`.
See [the official doc](https://github.com/minerllabs/competition_submission_template#what-should-my-code-structure-be-like-)
for detailed information.
pfrl_rainbow's avatar
pfrl_rainbow committed
24

pfrl_rainbow's avatar
pfrl_rainbow committed
25
Then you can create a submission by making a tag push to your repository on https://gitlab.aicrowd.com/. Any tag push (where the tag name begins with "submission-") to your repository is considered as a submission.
pfrl_rainbow's avatar
pfrl_rainbow committed
26
27
28

![](https://i.imgur.com/FqScw4m.png)

pfrl_rainbow's avatar
pfrl_rainbow committed
29
30
If everything works out correctly, you should be able to see your score on the
[competition leaderboard](https://www.aicrowd.com/challenges/neurips-2020-minerl-competition/leaderboards).
pfrl_rainbow's avatar
pfrl_rainbow committed
31

pfrl_rainbow's avatar
pfrl_rainbow committed
32
![MineRL Leaderboard](assets/minerl-leaderboard.png)
pfrl_rainbow's avatar
pfrl_rainbow committed
33
34


pfrl_rainbow's avatar
pfrl_rainbow committed
35
# About Baseline Algorithm
pfrl_rainbow's avatar
pfrl_rainbow committed
36

pfrl_rainbow's avatar
pfrl_rainbow committed
37
This baseline consists of two main steps:
pfrl_rainbow's avatar
pfrl_rainbow committed
38

pfrl_rainbow's avatar
pfrl_rainbow committed
39
40
1. [Apply K-means clustering](https://minerl.io/docs/tutorials/k-means.html) for the action space with the demonstration dataset.
2. Apply Rainbow algorithm on the discretized action space.
pfrl_rainbow's avatar
pfrl_rainbow committed
41

pfrl_rainbow's avatar
pfrl_rainbow committed
42
43
44
45
Each of steps utilizes existing libraries.  
K-means in the step 1 is from [scikit-learn](https://scikit-learn.org/stable/modules/generated/sklearn.cluster.KMeans.html#sklearn.cluster.KMeans),
and Rainbow in the spte 2 is from [PFRL](https://github.com/pfnet/pfrl),
which is a Pytorch-based RL library.
pfrl_rainbow's avatar
pfrl_rainbow committed
46
47


pfrl_rainbow's avatar
pfrl_rainbow committed
48
# How to Train Baseline Agent on your own
pfrl_rainbow's avatar
pfrl_rainbow committed
49

pfrl_rainbow's avatar
pfrl_rainbow committed
50
`mod/` directory contains all you need to train agent locally:
pfrl_rainbow's avatar
pfrl_rainbow committed
51

pfrl_rainbow's avatar
pfrl_rainbow committed
52
53
```bash
pip install numpy scipy scikit-learn pandas tqdm joblib pfrl
pfrl_rainbow's avatar
pfrl_rainbow committed
54

pfrl_rainbow's avatar
pfrl_rainbow committed
55
56
# Don't forget to set this!
export MINERL_DATA_ROOT=<directory you want to store demonstration dataset>
pfrl_rainbow's avatar
pfrl_rainbow committed
57

pfrl_rainbow's avatar
pfrl_rainbow committed
58
59
60
61
62
63
python3 mod/dqn_family.py \
  --gpu 0 --env "MineRLObtainDiamondDenseVectorObf-v0"  \
  --outdir result \
  --noisy-net-sigma 0.5 --arch distributed_dueling --replay-capacity 300000 --replay-start-size 5000 --target-update-interval 10000 \
  --num-step-return 10 --agent CategoricalDoubleDQN --monitor --lr 0.0000625 --adam-eps 0.00015 --prioritized --frame-stack 4 --frame-skip 4 \
  --gamma 0.99 --batch-accumulator mean
pfrl_rainbow's avatar
pfrl_rainbow committed
64

pfrl_rainbow's avatar
pfrl_rainbow committed
65
```
pfrl_rainbow's avatar
pfrl_rainbow committed
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98


# Team

The quick-start kit was authored by 
**[Shivam Khandelwal](https://twitter.com/skbly7)** with help from [William H. Guss](http://wguss.ml)

The competition is organized by the following team:

* [William H. Guss](http://wguss.ml) (Carnegie Mellon University)
* Mario Ynocente Castro (Preferred Networks)
* Cayden Codel (Carnegie Mellon University)
* Katja Hofmann (Microsoft Research)
* Brandon Houghton (Carnegie Mellon University)
* Noboru Kuno (Microsoft Research)
* Crissman Loomis (Preferred Networks)
* Keisuke Nakata (Preferred Networks)
* Stephanie Milani (University of Maryland, Baltimore County and Carnegie Mellon University)
* Sharada Mohanty (AIcrowd)
* Diego Perez Liebana (Queen Mary University of London)
* Ruslan Salakhutdinov (Carnegie Mellon University)
* Shinya Shiroshita (Preferred Networks)
* Nicholay Topin (Carnegie Mellon University)
* Avinash Ummadisingu (Preferred Networks)
* Manuela Veloso (Carnegie Mellon University)
* Phillip Wang (Carnegie Mellon University)


<img src="https://d3000t1r8yrm6n.cloudfront.net/images/challenge_partners/image_file/35/CMU_wordmark_1500px-min.png" width="50%"> 

  <img src="https://d3000t1r8yrm6n.cloudfront.net/images/challenge_partners/image_file/34/MSFT_logo_rgb_C-Gray.png" width="20%" style="margin-top:10px">

 <img src="https://raw.githubusercontent.com/AIcrowd/AIcrowd/master/app/assets/images/misc/aicrowd-horizontal.png" width="20%">   <img src="https://d3000t1r8yrm6n.cloudfront.net/images/challenge_partners/image_file/38/PFN_logo.png" width="15%" style="margin-top:10px">