SirStone/SirRoboGarage
1
0
Fork 0
Code Issues 28 Pull Requests Actions Projects Releases Wiki Activity

feat(SAC_LSTM_Bot): weight persistence module (#46)

Browse Source 
Save/load all SAC-LSTM tensors (actor, 2 critics, 2 target critics,
alpha, Adam states) into a single .zip of .npy files. Atomic write
via temp path + rename. Adam types (AdamVar, SACAdamStates) defined
here for training.nim to use.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Davide Cappellini
2026-08-20 23:57:13 +02:00
parent 55ef22ff8b
commit 54b8139b11
3 changed files with 496 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
SAC_LSTM_Bot/config.nims
+3
View File
@@ -1,6 +1,9 @@
# Static-link OpenBLAS for portable deployment
# ponytail: adjust path per machine, or use pkg-config
switch("passL", "-L/nix/store/v07svn2y92bvzjl51aj7c9ca1cwg7rw7-openblas-0.3.32/lib -lopenblas")
# libzip for weight checkpoint zip files
# ponytail: nix store path; adjust per machine, or use pkg-config
switch("passL", "-L/nix/store/wqvz31s598bvj3zb747943xhl38hjc6h-libzip-1.11.4/lib -lzip")
switch("threads", "on")
# begin Nimble config (version 2)
when withDir(thisDir(), system.fileExists("nimble.paths")):