Skip to content

Clarify curriculum and behavior name #3380

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

Merged
merged 2 commits into from
Feb 7, 2020
Merged

Clarify curriculum and behavior name #3380

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
091913a
clarify curriculum and behavior name
Feb 7, 2020
af1d2ac
doc some other missing fields too
Feb 7, 2020
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
12 changes: 10 additions & 2 deletions docs/Learning-Environment-Design-Agents.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -532,6 +532,9 @@ called independently of the `Max Step` property.

* `Behavior Parameters` - The parameters dictating what Policy the Agent will
receive.
* `Behavior Name` - The identifier for the behavior. Agents with the same behavior name
will learn the same policy. If you're using [curriculum learning](Training-Curriculum-Learning.md),
this is used as the top-level key in the config.
* `Vector Observation`
* `Space Size` - Length of vector observation for the Agent.
* `Stacked Vectors` - The number of previous vector observations that will
Expand All @@ -548,8 +551,13 @@ receive.
* `Model` - The neural network model used for inference (obtained after
training)
* `Inference Device` - Whether to use CPU or GPU to run the model during inference
* `Use Heuristic` - If checked, the Agent will use its 'Heuristic()' method for
decisions.
* `Behavior Type` - Determines whether the Agent will do training, inference, or use its
Heuristic() method:
* `Default` - the Agent will train if they connect to a python trainer, otherwise they will performance inference.
* `Heuristic Only` - the Agent will always use the `Heuristic()` method.
* `Inference Only` - the Agent will always perform inference.
* `Team ID` - Used to define the team for [self-play](Training-Self-Play.md)
* `Use Child Sensors` - Whether to use all Sensor components attached to child GameObjects of this Agent.
* `Max Step` - The per-agent maximum number of steps. Once this number is
reached, the Agent will be reset.

Expand Down
4 changes: 3 additions & 1 deletion docs/Training-Curriculum-Learning.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -68,7 +68,9 @@ SmallWallJump:
small_wall_height: [1.5, 2.0, 2.5, 4.0]
```

At the top level of the config is the behavior name. The curriculum for each
At the top level of the config is the behavior name. Note that this must be the
same as the Behavior Name in the [Agent's Behavior Parameters](Learning-Environment-Design-Agents.md#agent-properties).
The curriculum for each
behavior has the following parameters:
* `measure` - What to measure learning progress, and advancement in lessons by.
* `reward` - Uses a measure received reward.
Expand Down