README.md 10.8 KB
Newer Older
Benjamin Beyret's avatar
Benjamin Beyret committed
1
2
3
4
5
# Animal-AI Olympics

## Overview

Welcome to the repository for the Animal-AI Olympics competition where you will find all the code needed to compete in 
6
7
this new challenge. Note that for the moment this repo contains **only the training environment** (v0.5) that will be 
used for the competition and **does not contain any competition tests or information for entering**. If everything goes 
8
9
well the competition will be live on July 1st. Until then we will be continually updating with bug fixes and small 
changes to the environment. However, the general structure will stay the same so it's not too early to start working with the environment. For more information on the competition itself and to stay updated with any developments, head to the 
10
11
12
13
14
15
16
17
18
19
20
21
22
[Competition Website](http://www.animalaiolympics.com/) and follow [@MacroPhilosophy](https://twitter.com/MacroPhilosophy) 
and [@BenBeyret](https://twitter.com/BenBeyret) on twitter.

The environment contains an agent enclosed in a fixed sized arena. Objects can spawn in this arena, including positive 
and negative rewards (green, yellow and red spheres). 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, but part of the challenge will be experimenting and designing new configurations.

The goal of this first release is to **seek feedback from the community** as well as to provide the environment for 
research prior to the launch of the competition itself. The competition version of the environment will be similar to 
this one, however we are open to suggestion (for minor changes) and especially bug reports! Head over to the 
[issues page](https://github.com/beyretb/AnimalAI-Olympics/issues) and open a ticket using the `suggestion` or `bug` 
labels respectively.
Benjamin Beyret's avatar
Benjamin Beyret committed
23
24
25

To get started install the requirements below, and then follow the [Quick Start Guide](documentation/quickstart.md). 
A more in depth documentation <!--, including a primer on animal cognition,--> can be found on the 
26
[Documentation Page](documentation/README.md).
Benjamin Beyret's avatar
Benjamin Beyret committed
27

mdcrosby's avatar
mdcrosby committed
28
29
## Development Blog

30
31
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
32
33
34
35
36

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

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

37
38
3. [The Syllabus (Part 2): Lights Out](https://mdcrosby.com/blog/animalai3.html)

Benjamin Beyret's avatar
Benjamin Beyret committed
39
40
## Requirements

41
The Animal-AI package works on Linux, Mac and Windows, as well as most Cloud providers. 
42
<!--, for cloud engines check out [this cloud documentation](documentation/cloud.md).-->
Benjamin Beyret's avatar
Benjamin Beyret committed
43

Benjamin Beyret's avatar
Benjamin Beyret committed
44
First of all your will need `python3.6` installed. We recommend using a virtual environment specifically for the competition. Clone this repository to run the examples we provide you with. We offer two packages for 
45
this competition:
Benjamin Beyret's avatar
Benjamin Beyret committed
46

47
48
49
50
- The main one is an API for interfacing with the Unity environment. It contains both a 
[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:
51
52
53
54
    ```
    pip install animalai
    ```
    Or you can install it from the source, head to `animalai/` folder and run `pip install -e .`
55
56
57
58
59
60
61
62

- We also provide a package that can be used as a starting point for training, and which is required to run most of the 
example scripts found in the `examples/` folder. It contains an extension of 
[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:
63
64
65
66
    ```
    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
67

Benjamin Beyret's avatar
Benjamin Beyret committed
68
Finally download the environment for your system:
Benjamin Beyret's avatar
Benjamin Beyret committed
69
70
71

| OS | Environment link |
| --- | --- |
Benjamin Beyret's avatar
Benjamin Beyret committed
72
73
74
| 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
75

76
77
78
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
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93

## 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   |

94
95
## Competition Tests

96
97
98
99
100
101
102
We will be releasing further details about the tests in the competition over the coming weeks. The tests will be split 
into multiple categories from the very simple (e.g. **food retrieval**, **preferences**, and **basic obstacles**) to 
the more complex (e.g. **working memory**, **spatial memory**, **object permanence**, and **object manipulation**). For 
now we have included multiple example config files that each relate to a different category. As we release further 
details we will also specify the rules for the type of tests that can appear in each category. 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 categories but it would be off to a very good start.
103

mdcrosby's avatar
mdcrosby committed
104
105
## Citing

106
For now please cite the [Nature: Machine Intelligence piece](https://rdcu.be/bBCQt) for any work involving the competition environment: 
mdcrosby's avatar
mdcrosby committed
107

108
109
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
110

Benjamin Beyret's avatar
Benjamin Beyret committed
111
112
113
114
115
## 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 
116
117
118
[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
119

120
121
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
122

123
## Known Issues
124

125
126
127
In play mode pressing `R` or `C` does nothing sometimes. This is due to the fact that we have synchronized these 
features with the agent's frames in order to have frames in line with the configuration files for events such as lights 
off. **Solution**: press the key again, several times if needed.
128

129
130
~~When a lot of objects are spawned randomly, extremely rarely, the agent will fall through the floor.~~ (fixed in 
v0.6.1)
131

132
133
## TODO

Benjamin Beyret's avatar
Benjamin Beyret committed
134
- [x] Add inference viewer to the environment
135
- [x] Offer a gym wrapper for training
Benjamin Beyret's avatar
Benjamin Beyret committed
136
- [x] Improve the way the agent spawns
Benjamin Beyret's avatar
Benjamin Beyret committed
137
- [x] Add lights out configurations.
mdcrosby's avatar
mdcrosby committed
138
139
- [x] Improve environment framerates
- [x] Add moving food
mdcrosby's avatar
mdcrosby committed
140

Benjamin Beyret's avatar
Benjamin Beyret committed
141
## Version History
Benjamin Beyret's avatar
Benjamin Beyret committed
142

Benjamin Beyret's avatar
Benjamin Beyret committed
143
144
- v1.0
    - Adds inference mode to the environment to visualize trained agents
145
146
147
148
149

- 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 
150
    - Adds score in playmode (current and previous scores)
Benjamin Beyret's avatar
Benjamin Beyret committed
151
    - Playmode now incorporates lights off directly (in `examples` try: `python visualizeArena.py configs/lightsOff.yaml`)
152
153
154
    - 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
155
156
157
    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
158

Benjamin's avatar
Benjamin committed
159
- v0.5 Package `animalai`, gym compatible, dopamine example, bug fixes
160
161
162
163
164
165
166
167
    - 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
168
169
170
- 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`)
171
172
173
174
    - 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
175
    - The agent is now a ball rather than a cube
Benjamin Beyret's avatar
Benjamin Beyret committed
176
    - Increased safety for spawning the agent to avoid infinite loops
Benjamin Beyret's avatar
Benjamin Beyret committed
177
178
    - Bugs fixes
    
Benjamin Beyret's avatar
Benjamin Beyret committed
179
- v0.3 - Lights off, remove Beams and add cylinder
180
181
    - 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
182
    - visualizeLightsOff.py displays an example of lights off, from the agent's point of view
Benjamin Beyret's avatar
Benjamin Beyret committed
183
184
    - Beams objects have been removed
    - A `Cylinder` object has been added (similar behaviour to the `Woodlog`)
Benjamin Beyret's avatar
Benjamin Beyret committed
185
    - The immovable `Cylinder` tunnel has been renamed `CylinderTunnel`
Benjamin Beyret's avatar
Benjamin Beyret committed
186
    - `UnityEnvironment.reset()` parameter `config` renamed to `arenas_configurations_input`
Benjamin Beyret's avatar
Benjamin Beyret committed
187
    
mdcrosby's avatar
mdcrosby committed
188
189
- 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
190
    [the details here](documentation/definitionsOfObjects.md#rewards).
mdcrosby's avatar
mdcrosby committed
191
192
193
    - 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
194
195

- v0.1 - Initial Release
Benjamin Beyret's avatar
Benjamin Beyret committed
196