README.md 14.6 KB
Newer Older
Benjamin Beyret's avatar
Benjamin Beyret committed
1
2
# Animal-AI Olympics

Matthew Crosby's avatar
Matthew Crosby committed
3
4
5
6
<p align="center">
  <img height="300" src="documentation/PrefabsPictures/steampunkFOURcrop.png">
</p>

7
**July 1st - November 1st**
8

Matthew Crosby's avatar
Matthew Crosby committed
9
The Animal-AI Olympics is an AI competition with tests inspired by animal cognition. Participants are given a small environment with just seven different classes of objects that can be placed inside. In each test, the agent needs to retrieve the food in the environment, but to do so there are obstacles to overcome, ramps to climb, boxes to push, and areas that must be avoided. The real challenge is that we don't provide the tests in advance. It's up to you to explore the possibilities with the environment and build interesting configurations that can help create an agent that understands how the environment's physics work and the affordances that it has. The final submission should be an agent capable of robust food retrieval behaviour similar to that of many kinds of animals. We know the animals can pass these tests, it's time to see if AI can too.
10

11
12
13
14
15
16
17
18
19
20
21
22
## Prizes $32,000 (equivalent value)

* Overall Prizes
  * 1st place overall: **$7,500 total value** - $6,500 with up to $1,000 travel to speak at NeurIPS 2019.
  * 2nd place overall: **$6,000 total value** - $5,000 with up to $1,000 travel to speak at NeurIPS 2019.
  * 3rd place overall: **$1,500**.
* WBA-Prize: **$5,000 total value** - $4,000 with up to $1,000 travel to speak at NeurIPS 2019
* Category Prizes: **$200** For best performance in each category (cannot combine with other prizes - max 1 per team).
* **Mid-way AWS Research Credits**: The top 20 entries as of **September 1st** will be awarded **$500** of AWS credits.

See [competition launch page](https://mdcrosby.com/blog/animalailaunch.html) and official rules for further details.

Matthew Crosby's avatar
Matthew Crosby committed
23
**Important** Please check the competition rules [here](http://animalaiolympics.com/rules.html). **To submit to the competition and be considered for prizes you must also fill in [this form](https://forms.gle/PKCgp2JAWvjf4c9i6)**. Entry to the competition ([via EvalAI](https://evalai.cloudcv.org/web/challenges/challenge-page/396/overview)) constitutes agreement with all competition rules. 
24

Benjamin Beyret's avatar
Benjamin Beyret committed
25
26
## Overview

27
Here you will find all the code needed to compete in this new challenge. This repo contains **the training environment** (v1.0) that will be used for the competition. Information for entering can be found in the [submission documentation](documentation/submission.md). Please check back during the competition for minor bug-fixes and updates, but as of v1.0 the major features and contents are set in place.
28
29

For more information on the competition itself and to stay updated with any developments, head to the 
30
[Competition Website](http://www.animalaiolympics.com/) and follow [@MacroPhilosophy](https://twitter.com/MacroPhilosophy) and [@BenBeyret](https://twitter.com/BenBeyret) on twitter.
31
32

The environment contains an agent enclosed in a fixed sized arena. Objects can spawn in this arena, including positive 
33
and negative rewards (green, yellow and red spheres) that the agent must obtain (or avoid). All of the hidden tests that will appear in the competition are made using the objects in the training environment. We have provided some sample environment configurations that should be useful for training (see examples/configs), but part of the challenge is to experiment and design new configurations.
Benjamin Beyret's avatar
Benjamin Beyret committed
34
35

To get started install the requirements below, and then follow the [Quick Start Guide](documentation/quickstart.md). 
36
More in depth documentation can be found on the [Documentation Page](documentation/README.md).
Benjamin Beyret's avatar
Benjamin Beyret committed
37

38
39
40
41
## Evaluation

The competition has 300 tests, split over ten categories. The categories range from the very simple (e.g. **food retrieval**, **preferences**, and **basic obstacles**) to the more complex (e.g. **spatial reasoning**, **internal models**, **object permanence**, and **causal reasoning**). We have included example config files for the first seven categories. Note that the example config files are just simple examples to be used as a guide. An agent that solves even all of these perfectly may still not be able to solve all the tests in the category, but it would be off to a good start.

Matthew Crosby's avatar
Matthew Crosby committed
42
43
44
The submission website allows you to submit an agent that will be run on all 300 tests and it returns the overall score (number of tests passed) and score per category. We cannot offer infinite compute, so instances will be timed out after ~90 minutes and only tests performed up to that point counted (all others will be considered failed). See the [submission documentation](documentation/submission.md) for more information. 

For the mid-way and final evaluation we will (resources permitting) run more extensive testing with 3 variations per test (so 900 tests total). The variations will include minor perturbations to the configurations. The agent will have to pass all 3 variations to pass each individual test, giving a total score out of 300. This means that **your final test score might be lower than the score achieved during the competition** and that **the competition leaderboard on EvalAI may not exactly match the final results**. 
45

mdcrosby's avatar
mdcrosby committed
46
47
## Development Blog

48
You can read the launch posts - with information about prizes and the categories in the competition here:
49

Matthew Crosby's avatar
Matthew Crosby committed
50
[Animal-AI Evaluation: July 8th](https://mdcrosby.com/blog/animalaieval.html) - with collated information about the evaluation.
51
52

[Animal-AI Launch: July 1st](https://mdcrosby.com/blog/animalailaunch.html) - with information about the prizes and  introduction to all 10 categories.
53

54
55
You can read the development blog [here](https://mdcrosby.com/blog). It covers further details about the competition as 
well as part of the development process.
mdcrosby's avatar
mdcrosby committed
56
57
58
59
60

1. [Why Animal-AI?](https://mdcrosby.com/blog/animalai1.html)

2. [The Syllabus (Part 1)](https://mdcrosby.com/blog/animalai2.html)

61
62
3. [The Syllabus (Part 2): Lights Out](https://mdcrosby.com/blog/animalai3.html)

Benjamin Beyret's avatar
Benjamin Beyret committed
63
64
## Requirements

65
The Animal-AI package works on Linux, Mac and Windows, as well as most Cloud providers. Note that for submission to the competition we only support linux-based Docker files.  
66
<!--, for cloud engines check out [this cloud documentation](documentation/cloud.md).-->
Benjamin Beyret's avatar
Benjamin Beyret committed
67

68
We recommend using a virtual environment specifically for the competition. You will need `python3.6` installed (we currently only support **python3.6**). Clone this repository to run the examples we provide.
Benjamin Beyret's avatar
Benjamin Beyret committed
69

70
71
72
We offer two packages for this competition:

- The main package is an API for interfacing with the Unity environment. It contains both a 
73
74
75
[gym environment](https://github.com/openai/gym) as well as an extension of Unity's 
[ml-agents environments](https://github.com/Unity-Technologies/ml-agents/tree/master/ml-agents-envs). You can install it
 via pip:
76
77
78
79
    ```
    pip install animalai
    ```
    Or you can install it from the source, head to `animalai/` folder and run `pip install -e .`
80

Guikarist's avatar
Guikarist committed
81
82
83
84
85
    We also provide an `env.yml` by which you can install it via conda:
    ```
    conda env create -f env.yml
    ```

86
- We also provide a package that can be used as a starting point for training, and which is required to run most of the 
Matthew Crosby's avatar
Matthew Crosby committed
87
example scripts found in the `examples/` folder. At the moment **we only support Linux and Max** for the training examples. It contains an extension of 
88
89
90
91
92
[ml-agents' training environment](https://github.com/Unity-Technologies/ml-agents/tree/master/ml-agents) that relies on 
[OpenAI's PPO](https://openai.com/blog/openai-baselines-ppo/), as well as 
[Google's dopamine](https://github.com/google/dopamine) which implements 
[Rainbow](https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/download/17204/16680) (among others). You can also install 
this package using pip:
93
94
95
96
    ```
    pip install animalai-train
    ```
    Or you can install it from source, head to `examples/animalai_train` and run `pip install -e .`
Benjamin Beyret's avatar
Benjamin Beyret committed
97

Benjamin Beyret's avatar
Benjamin Beyret committed
98
Finally download the environment for your system:
Benjamin Beyret's avatar
Benjamin Beyret committed
99
100
101

| OS | Environment link |
| --- | --- |
Benjamin Beyret's avatar
Benjamin Beyret committed
102
103
104
| Linux |  [download v1.0.0](https://www.doc.ic.ac.uk/~bb1010/animalAI/env_linux_v1.0.0.zip) |
| MacOS |  [download v1.0.0](https://www.doc.ic.ac.uk/~bb1010/animalAI/env_mac_v1.0.0.zip) |
| Windows | [download v1.0.0](https://www.doc.ic.ac.uk/~bb1010/animalAI/env_windows_v1.0.0.zip)  |
Benjamin Beyret's avatar
Benjamin Beyret committed
105

106
107
108
You can now unzip the content of the archive to the `env` folder and you're ready to go! Make sure the executable 
`AnimalAI.*` is in `env/`. On linux you may have to make the file executable by running `chmod +x env/AnimalAI.x86_64`. 
Head over to [Quick Start Guide](documentation/quickstart.md) for a quick overview of how the environment works.
Benjamin Beyret's avatar
Benjamin Beyret committed
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123

## Manual Control

If you launch the environment directly from the executable or through the VisualizeArena script it will launch in player 
mode. Here you can control the agent with the following:

| Keyboard Key  | Action    |
| --- | --- |
| W   | move agent forwards |
| S   | move agent backwards|
| A   | turn agent left     |
| D   | turn agent right    |
| C   | switch camera       |
| R   | reset environment   |

mdcrosby's avatar
mdcrosby committed
124
125
## Citing

126
**Official Animal-AI Papers Coming Soon**. In the meantime please cite the [Nature: Machine Intelligence piece](https://rdcu.be/bBCQt) for any work involving the competition environment. 
mdcrosby's avatar
mdcrosby committed
127

128
129
Crosby, M., Beyret, B., Halina M. [The Animal-AI Olympics](https://www.nature.com/articles/s42256-019-0050-3) Nature 
Machine Intelligence 1 (5) p257 2019.
mdcrosby's avatar
mdcrosby committed
130

Benjamin Beyret's avatar
Benjamin Beyret committed
131
132
133
134
135
## Unity ML-Agents

The Animal-AI Olympics was built using [Unity's ML-Agents Toolkit.](https://github.com/Unity-Technologies/ml-agents)

The Python library located in [animalai](animalai) is almost identical to 
136
137
138
[ml-agents v0.7](https://github.com/Unity-Technologies/ml-agents/tree/master/ml-agents-envs). We only added the 
possibility to change the configuration of arenas between episodes. The documentation for ML-Agents can be found 
[here](https://github.com/Unity-Technologies/ml-agents/blob/master/docs/Python-API.md).
Benjamin Beyret's avatar
Benjamin Beyret committed
139

140
141
Juliani, A., Berges, V., Vckay, E., Gao, Y., Henry, H., Mattar, M., Lange, D. (2018). [Unity: A General Platform for 
Intelligent Agents.](https://arxiv.org/abs/1809.02627) *arXiv preprint arXiv:1809.02627*
Benjamin Beyret's avatar
Benjamin Beyret committed
142

143
144
## EvalAI

Benjamin Beyret's avatar
Benjamin Beyret committed
145
The competition is kindly hosted on [EvalAI](https://github.com/Cloud-CV/EvalAI), an open source web application for AI competitions. Special thanks to [Rishabh Jain](https://github.com/RishabhJain2018) for his help in settting this up.
146
147
148

Deshraj Yadav, Rishabh Jain, Harsh Agrawal, Prithvijit Chattopadhyay, Taranjeet Singh, Akash Jain, Shiv Baran Singh, Stefan Lee and Dhruv Batra (2019) [EvalAI: Towards Better Evaluation Systems for AI Agents](https://arxiv.org/abs/1902.03570)

149
## Known Issues
150

151
In play mode pressing `R` or `C` does nothing sometimes. This is due to the fact that we have synchronized these 
152
features with the agent's frames in order to have frames in line with the configuration files for elements such as blackouts. **Solution**: press the key again, several times if needed.
153

154
155
~~When a lot of objects are spawned randomly, extremely rarely, the agent will fall through the floor.~~ (fixed in 
v0.6.1)
156

157
158
## TODO

Benjamin Beyret's avatar
Benjamin Beyret committed
159
- [x] Add custom resolutions
Benjamin Beyret's avatar
Benjamin Beyret committed
160
- [x] Add inference viewer to the environment
161
- [x] Offer a gym wrapper for training
Benjamin Beyret's avatar
Benjamin Beyret committed
162
- [x] Improve the way the agent spawns
Benjamin Beyret's avatar
Benjamin Beyret committed
163
- [x] Add lights out configurations.
mdcrosby's avatar
mdcrosby committed
164
165
- [x] Improve environment framerates
- [x] Add moving food
mdcrosby's avatar
mdcrosby committed
166

Benjamin Beyret's avatar
Benjamin Beyret committed
167
## Version History
Benjamin Beyret's avatar
Benjamin Beyret committed
168

Benjamin Beyret's avatar
Benjamin Beyret committed
169
170
- v1.0.3
    - Adds inference mode to Gym environment
171
    - Adds seed to Gym Environment
172
173
174
    - Submission example folder containing a trained agent
    - Provide submission details for the competition
    - Documentation for training on AWS
Benjamin Beyret's avatar
Benjamin Beyret committed
175

176
177
- v1.0.2
    - Adds custom resolution for docker training as well
178
    - Fix version checker
179
180

- v1.0.0
Benjamin Beyret's avatar
Benjamin Beyret committed
181
    - Adds custom resolution to both Unity and Gym environments
Benjamin Beyret's avatar
Benjamin Beyret committed
182
    - Adds inference mode to the environment to visualize trained agents
Benjamin Beyret's avatar
Benjamin Beyret committed
183
184
    - Prizes announced
    - More details about the competition
185
186
187
188
189

- v0.6.1 (Environment only) 
    - Fix rare events of agent falling through the floor or objects flying in the air when resetting an arena

- v0.6.0 
190
    - Adds score in playmode (current and previous scores)
Benjamin Beyret's avatar
Benjamin Beyret committed
191
    - Playmode now incorporates lights off directly (in `examples` try: `python visualizeArena.py configs/lightsOff.yaml`)
192
193
194
    - To simplify the environment several unnecessary objects have been removed [see here](documentation/definitionsOfObjects.md)
    - **Several object properties have been changed** [also here](documentation/definitionsOfObjects.md)
    - Frames per action reduced from 5 to 3 (*i.e.*: for each action you send we repeat it for a certain number of frames 
Benjamin Beyret's avatar
Benjamin Beyret committed
195
196
197
    to ensure smooth physics)
    - Add versions compatibility check between the environment and API
    - Remove `step_number` argument from `animalai.environment.step`
Benjamin Beyret's avatar
Benjamin Beyret committed
198

Benjamin's avatar
Benjamin committed
199
- v0.5 Package `animalai`, gym compatible, dopamine example, bug fixes
200
201
202
203
204
205
206
207
    - Separate environment API and training API in Python
    - Release both as `animalai` and `animalai-train` PyPI packages (for `pip` installs)
    - Agent speed in play-mode constant across various platforms
    - Provide Gym environment
    - Add `trainBaselines,py` to train using `dopamine` and the Gym wrapper
    - Create the `agent.py` interface for agents submission
    - Add the `HotZone` object (equivalent to the red zone but without death)

Benjamin Beyret's avatar
Benjamin Beyret committed
208
209
210
- v0.4 - Lights off moved to Unity, colors configurations, proportional goals, bugs fixes
    - The light is now directly switched on/off within Unity, configuration files stay the same
    - Blackouts now work with infinite episodes (`t=0`)
211
212
213
214
    - The `rand_colors` configurations have been removed and the user can now pass `RGB` values, see 
    [here](documentation/configFile.md#objects)
    - Rewards for goals are now proportional to their size (except for the `DeathZone`), see 
    [here](documentation/definitionsOfObjects.md#rewards)
Benjamin Beyret's avatar
Benjamin Beyret committed
215
    - The agent is now a ball rather than a cube
Benjamin Beyret's avatar
Benjamin Beyret committed
216
    - Increased safety for spawning the agent to avoid infinite loops
Benjamin Beyret's avatar
Benjamin Beyret committed
217
218
    - Bugs fixes
    
Benjamin Beyret's avatar
Benjamin Beyret committed
219
- v0.3 - Lights off, remove Beams and add cylinder
220
221
    - We added the possibility to switch the lights off at given intervals, see 
    [here](documentation/configFile.md#blackouts)
Benjamin Beyret's avatar
Benjamin Beyret committed
222
    - visualizeLightsOff.py displays an example of lights off, from the agent's point of view
Benjamin Beyret's avatar
Benjamin Beyret committed
223
224
    - Beams objects have been removed
    - A `Cylinder` object has been added (similar behaviour to the `Woodlog`)
Benjamin Beyret's avatar
Benjamin Beyret committed
225
    - The immovable `Cylinder` tunnel has been renamed `CylinderTunnel`
Benjamin Beyret's avatar
Benjamin Beyret committed
226
    - `UnityEnvironment.reset()` parameter `config` renamed to `arenas_configurations_input`
Benjamin Beyret's avatar
Benjamin Beyret committed
227
    
mdcrosby's avatar
mdcrosby committed
228
229
- v0.2 - New moving food rewards, improved Unity performance and bug fixes 
    - Moving rewards have been added, two for each type of reward, see 
Benjamin Beyret's avatar
Benjamin Beyret committed
230
    [the details here](documentation/definitionsOfObjects.md#rewards).
mdcrosby's avatar
mdcrosby committed
231
232
233
    - Added details for the maze generator.
    - Environment performance improved.
    - [Issue #7](../../issues/7) (`-inf` rewards for `t: 0` configuration) is fixed.
Benjamin Beyret's avatar
Benjamin Beyret committed
234
235

- v0.1 - Initial Release
Benjamin Beyret's avatar
Benjamin Beyret committed
236