Tutorials: Building Toolkit

[These video tutorials has been depreciated for it being difficult to maintain, please simply follow the instructions/documentations on the Github page which covers everything you need.]

Github: Arena-BuildingToolkit

[New Feature] Lidar Sensor

Lidar sensor is widely used in robots to get precise low dimensional representation of the surroundings.

Lidar sensor is suitable for robotic SLAM applications. It provides 360 degree scan field, certain rotating frequency with certain ranger distance. Lidar is the ideal sensor in cost sensitive areas like robots consumer and hardware hobbyist.

It is also recently used as a representation for game AI, see OpenAI Hide-and-seek.

[Note] When set ScanFramePerSecond to a positive number, you will still get all the data from lidar at each step, the difference is that some of the data is not refreshed, i.e., only part of data is refreshed at each step. This corresponding to the limited scan frequency of a real lidar sensor.

[New Feature] Visualize Vector Observation

After you add some vector observations to your agent, you may want to check if they make sense for the agent.

All ArenaAgent are equipped with this visualization tool by default.

It provides flexible ways to investigate/preview the vector observation.

It is only enabled in Unity editor, and will not slow down your game when it is compiled for the target platform.

[New Feature] Visualize Visual Observation

After you add some visual observations via AgentCamera prefab to your agent, you may want to check if the actual observation for agent (smaller and maybe in grayscale) makes sense.

All ArenaAgent are equipped with this visualization tool by default.

It provides flexible ways to investigate/preview the visual observation.

It is also supported in a compiled game, though not recommended, as it slows down your game.

The baseline side of Arena project provides better visualization tool for the compiled game.

[New Feature] Dynamically Change Social Tree Structure

Arena-BuildingToolkit now supports dynamically change social tree structure, during an episode, or at the reset of an episode.

This could open up an interesting research direction of multi-agent learning with agents dies or newly born dynamically. We temporally refer to this kind of problem as "social lifelong learning", in contrast to "lifelong learning" in the context of single agent learning. Say: Can the agent learns to give birth to a specific number of babies, based on the resources it has and the stage of the society / population.

[Get Started 1] Setup the Workspace [Video contains names, temporally hidden for review policy]

Setup the workspace with Unity Editor.

Editor Version: Unity 2018.3.6f1 Personal, download here.
./Assets/ArenaSDK: main content of the project.
Outside ./Assets/ArenaSDK: some temporal draft that will be cleaned up in the future.

[Get Started 2] Create a Simple One Player Game

Learn building new learning environments with few lines of code.

Before you start, we are expecting you to have basic knowledge on Unity. Thus, you are recommended to finish the Roll-a-ball tutorial to learn some basic concepts of Unity.
GlobalManager: manager every global settings, as the parent of everything.

[Get Started 3] Create a Simple Two Players Game

Build a two players game and understand ArenaNode.

ArenaNode: a node in the social tree to manage the reward of its child nodes and the life cycle of its child nodes.
ArenaAgent: each individual actual acting agent.

[Advanced] Upgrade/Change Version of ML-Agents

How to upgrade or change the version of the Unity ML-Agent dependence.

Override "Assets/ML-Agents" with the the recent ML-Agent folder here.

Apply several changes in ML-Agent:

change "public BroadcastHub broadcastHub = new BroadcastHub();" in "Assets/ML-Agents/Scripts/Academy.cs" to "[HideInInspector] public BroadcastHub broadcastHub = new BroadcastHub();"
change "AgentInfo info;" in "Assets/ML-Agents/Scripts/Agent.cs" to "protected AgentInfo info;"
change "AgentInfo m_Info;" in "Assets/ML-Agents/Scripts/Agent.cs" to "protected AgentInfo info;"

[Advanced] Handling Variants of Your Games Efficiently

How to handle different configurations of your games with prefabs and prefab variants.

Prefab - GlobalManager in "Assets/ArenaSDK/Prefabs/" handles settings of all games.
Prefab Variant - GlobalManager Variant in "Assets/ArenaSDK/GameSet/[cool_game]/" handles settings of the specific game [cool_game].

[Reward Function] Reward Function Based on Distance

Use reward function based on distance.

Use Dense Reward Functions

Use multiple off-the-shelf dense reward functions.

Use More Agent Prefabs

Use multiple off-the-shelf agent prefabs in Arena-BuildingToolkit.

[New Agent] Snake Agent

Snake is the common name for a video game concept where the player maneuvers a line which grows in length, with the line itself being a primary obstacle. The concept originated in the 1976 arcade game Blockade, and the ease of implementing Snake has led to hundreds of versions (some of which have the word snake or worm in the title) for many platforms. See Wiki Page.

Make Your Game More Neat with Prefabs

Suggestions on how to prefab you game so that you can enjoy cleaner project.

Log Information

Identify where the log information comes from.

Set NodeID

Set valid NodeID.

Agent Camera Display Mode

Select mode of which multiple cameras are displayed in the window

Import: come with GlobalManager.
[Depreciated] AgentCameraDisplayMode = AgentCameraDisplayModes.All: all cameras are aligned automatically to fit in the single window.
AgentCameraDisplayMode = AgentCameraDisplayModes.Single: one camera takes the whole window at one time, press F1 and F2 to navigate among different cameras .

UI Percentage Bar [Video contains names, temporally hidden for review policy]

Display percentage or / and value with HUD display.

Import: Drag prefab UIPercentageBar in scene as a child of the canvas of the AgentCamera, then it is ready to use via ArenaAgent.UIPercentageBars[UIPercentageBar.ID]. Or Drag prefab UIPercentageBar in scene as a child of the canvas of the TopDownCamera, then it is ready to use via GlobalManager.UIPercentageBars[UIPercentageBar.ID].
UIPercentageBar.ID: set an ID for this UIPercentageBar.
ArenaAgent.UIPercentageBars[UIPercentageBar.ID].UpdatePercentage(float Percentage_): Update the percentage to display.
ArenaAgent.UIPercentageBars[UIPercentageBar.ID].UpdateValue(float Value_): Update the percentage to display by value, the value is automatically normalized to a percentage. The min UIPercentageBar.getMinValue() and max UIPercentageBar.getMaxValue() of the value will also be displayed.

Use Gun to Attack

Use gun to fire a bullet, which will kill an agent.

Show Aim Line

Show an aim line for visualizing your gun attack.

Gun Attack with Raycast

Use Raycast for gun attack, which is safer and more efficient.

Use Eatable Prefabs

Add eatable objects to the game.

Use Transform Reinitializers

Use transform reinitializers to re-initialize objects at the reset of each episode.

Playground with Maze

A playground with randomly regenerated maze at the every episode.

Playground with Barriers

A playground with randomly regenerated barriers at the every episode.

[Global Randomization] Light

Randomize all lights in the game.

[Global Randomization] Physical Properties

Randomize physical properties in the game.

Compile Game to Binary File [Video contains names, temporally hidden for review policy]

Compile your game to a binary file, and train with Arena-Baselines.

More to come...

Page updated

Google Sites

Report abuse

This site uses cookies from Google to deliver its services and to analyze traffic. Information about your use of this site is shared with Google. By clicking "accept", you agree to its use of cookies. Cookie Policy

Reject