tdpeuter/2026SEL3-project-Brittle_Star_Controller_Modularity
tdpeuter/2026SEL3-project-Brittle_Star_Controller_Modularity
Archived
1
Fork 0
Code Issues Releases Activity

Update docs/design/actor-critic.md

Browse source 
Co-authored-by: RobinMeersman <77965843+RobinMeersman@users.noreply.github.com>
This commit is contained in:
Tibo De Peuter 2026-05-20 15:24:10 +02:00 • committed by GitHub
parent 6d4a05e1bb
commit 50bc3bf20b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
docs/design/actor-critic.md
View file

@ -104,7 +104,7 @@ The MLPs used in both pipelines are defined with specific hidden layer configura
and computational cost. As of right now, though this might change as we make progress in our experiments, we use: and computational cost. As of right now, though this might change as we make progress in our experiments, we use:
- Input Networks (Sensors & Feature Extractors): These networks map the raw state inputs to internal hidden states. - Input Networks (Sensors & Feature Extractors): These networks map the raw state inputs to internal hidden states.
They are configured as standard dense networks with 2 hidden layers of 64 nodes each (`[64, 64]`) and utilize `tanh` They are configured as standard dense networks with 3 hidden layers of 300 nodes each (`[300, 300, 300]`) and utilize `tanh`
activation functions. activation functions.
- Output Networks (Motors, Actors & Critics): The final output models are intentionally kept shallow. The Actor - Output Networks (Motors, Actors & Critics): The final output models are intentionally kept shallow. The Actor
directly projects the hidden state to a continuous action distribution (`mean` and `log_std`) using a single dense directly projects the hidden state to a continuous action distribution (`mean` and `log_std`) using a single dense