From e4211ca04ee5bc18ffade1e8596a6f247b918493 Mon Sep 17 00:00:00 2001 From: Ruo-Ping Dong Date: Tue, 25 May 2021 10:15:11 -0700 Subject: [PATCH 1/2] update sensor stacking doc --- docs/Learning-Environment-Design-Agents.md | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/docs/Learning-Environment-Design-Agents.md b/docs/Learning-Environment-Design-Agents.md index f09f46074e..109ccf95b5 100644 --- a/docs/Learning-Environment-Design-Agents.md +++ b/docs/Learning-Environment-Design-Agents.md @@ -370,9 +370,6 @@ The steps for enabling stacking depends on how you generate observations: Generally, this should happen in the `CreateSensor()` method of your `SensorComponent`. -Note that stacking currently only supports for vector observations; stacking -for visual observations is not supported. - #### Vector Observation Summary & Best Practices - Vector Observations should include all variables relevant for allowing the @@ -432,6 +429,10 @@ have a unique name so that they can be sorted deterministically (the name must be unique for that Agent, but multiple Agents can have a Sensor Component with the same name). +Visual observations also supports stacking, bu specifying `Observation Stacks` +to a value greater than 1. The visual observations from the last `stackSize-1` +steps will be stacked on the last dimension (channel dimension). + When using `RenderTexture` visual observations, a handy feature for debugging is adding a `Canvas`, then adding a `Raw Image` with it's texture set to the Agent's `RenderTexture`. This will render the agent observation on the game From 814cebc1250f4804e9e199a27085b5add0455687 Mon Sep 17 00:00:00 2001 From: Ruo-Ping Dong Date: Tue, 25 May 2021 11:02:35 -0700 Subject: [PATCH 2/2] Update docs/Learning-Environment-Design-Agents.md Co-authored-by: Chris Elion --- docs/Learning-Environment-Design-Agents.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/Learning-Environment-Design-Agents.md b/docs/Learning-Environment-Design-Agents.md index 109ccf95b5..f0bffae693 100644 --- a/docs/Learning-Environment-Design-Agents.md +++ b/docs/Learning-Environment-Design-Agents.md @@ -429,7 +429,7 @@ have a unique name so that they can be sorted deterministically (the name must be unique for that Agent, but multiple Agents can have a Sensor Component with the same name). -Visual observations also supports stacking, bu specifying `Observation Stacks` +Visual observations also support stacking, by specifying `Observation Stacks` to a value greater than 1. The visual observations from the last `stackSize-1` steps will be stacked on the last dimension (channel dimension).