From 90902a582e888cc82c003e92ab78303b74846df8 Mon Sep 17 00:00:00 2001 From: Ivan-267 <61947090+Ivan-267@users.noreply.github.com> Date: Wed, 22 Jan 2025 05:08:29 +0100 Subject: [PATCH 1/2] Update FAQ Adds information about the env occasionally freezing during training. --- README.md | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/README.md b/README.md index 60e9b756..1d6a0978 100644 --- a/README.md +++ b/README.md @@ -150,6 +150,10 @@ If the README and docs here not provide enough information, reach out to us on [ We are inspired by the the Unity ML agents toolkit and we aim to provide a more compact, concise and hackable codebase, with little abstraction. +### The environment appears to freeze periodically during training, why does it happen? + +With the default, SB3 training script, it's normal for the Godot env to freeze ocassionally while the model is updating. + # License Godot RL Agents is MIT licensed. See the [LICENSE file](https://www.notion.so/huggingface2/LICENSE) for details. From 4824db3fd9d7a735175c0293d52ef13ac51d5c03 Mon Sep 17 00:00:00 2001 From: Ivan-267 <61947090+Ivan-267@users.noreply.github.com> Date: Wed, 22 Jan 2025 05:12:34 +0100 Subject: [PATCH 2/2] Update README.md --- README.md | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 1d6a0978..d1715e42 100644 --- a/README.md +++ b/README.md @@ -150,9 +150,10 @@ If the README and docs here not provide enough information, reach out to us on [ We are inspired by the the Unity ML agents toolkit and we aim to provide a more compact, concise and hackable codebase, with little abstraction. -### The environment appears to freeze periodically during training, why does it happen? +### The environment appears to periodicallly freeze during training, why does it happen? -With the default, SB3 training script, it's normal for the Godot env to freeze ocassionally while the model is updating. +With the default SB3 training script, it's normal for the Godot env to periodically freeze while the model is updating. +Once the model is trained, if you save and/or export it to onnx, you can run inference from the trained model, which will run faster. # License