Skip to content

Adding example project hint to Discrete Action Mask section #4983

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 5 commits into from
Closed

Adding example project hint to Discrete Action Mask section #4983

Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
918282e
Masking Discrete Actions typos
philippds Feb 17, 2021
9c33906
Adding action masking example hint
philippds Feb 20, 2021
1ba7c58
Merge pull request #1 from Unity-Technologies/master
philippds Feb 20, 2021
8bc1718
Merge pull request #2 from Unity-Technologies/master
philippds Feb 22, 2021
5ed783c
Addint 'On Demand Decision' hint to the documentation
philippds Feb 22, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 5 additions & 1 deletion docs/Learning-Environment-Design-Agents.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -104,7 +104,9 @@ physics-based simulations. For example, an agent in a robotic simulator that
must provide fine-control of joint torques should make its decisions every step
of the simulation. On the other hand, an agent that only needs to make decisions
when certain game or simulation events occur, such as in a turn-based game,
should call `Agent.RequestDecision()` manually.
should call `Agent.RequestDecision()` manually. Take a look at the [Bouncer environment](https://github.com/Unity-Technologies/ml-agents/blob/master/docs/Learning-Environment-Examples.md#bouncer)
wherein we have removed the decision requester component and call [RequestDecision manually](https://github.com/Unity-Technologies/ml-agents/blob/master/Project/Assets/ML-Agents/Examples/Bouncer/Scripts/BouncerAgent.cs#L79).
We call this 'On Demand decisions'.

## Observations and Sensors
In order for an agent to learn, the observations should include all the
Expand Down Expand Up @@ -695,6 +697,8 @@ are masked)
WriteMask(0, new int[2]{1,2});
```

If you are looking for an example project where this is implemented, our [Gridworld](https://github.com/Unity-Technologies/ml-agents/blob/master/Project/Assets/ML-Agents/Examples/GridWorld/Scripts/GridAgent.cs#L39) example environment uses action masking.

Notes:

- You can call `WriteMask` multiple times if you want to put masks on multiple
Expand Down