fix(PPO_Bot): radar oscillation, Adam persistence, checkpoint order, channel race

- enemy_tracker: toggle lastOvershootDir each tick; make getRadarTurnRate take var tracker
- training: remove threadvar Adam globals; pass adamStates as var param to ppoUpdate; export ACAdamStates
- PPO_Bot: carry ACAdamStates through TrainingArgs/TrainingResult; drop trainingDone bool and Lock — use resultChan.tryRecv() directly as synchronisation
- weights: sort checkpoint dirs newest-first by mtime instead of hardcoded order
- tests/test_training: pass explicit ACAdamStates to ppoUpdate

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-08-16 15:42:06 +02:00
parent 473d67f644
commit aea0724d3a
5 changed files with 74 additions and 62 deletions
+15 -6
View File
@@ -1,6 +1,6 @@
## weights.nim — save/load ActorCritic weights as .npy files.
import std/[os, times, strutils]
import std/[os, times, strutils, algorithm, sequtils]
import arraymancer
import ./network
@@ -70,12 +70,21 @@ proc saveCheckpoint*(ac: ActorCritic, weightsRoot: string, roundNum: int) =
saveWeightsAtomic(ac, weightsRoot / ("checkpoint_" & $slot))
proc loadBestAvailable*(ac: var ActorCritic, weightsRoot: string): bool =
## Try latest/, then checkpoint_3/, checkpoint_2/, checkpoint_1/.
## Try latest/ first, then checkpoints sorted newest-first by mtime.
## Returns true if weights loaded, false if all fail (random init stays).
for candidate in [weightsRoot / "latest",
weightsRoot / "checkpoint_3",
weightsRoot / "checkpoint_2",
weightsRoot / "checkpoint_1"]:
let checkpoints = [weightsRoot / "checkpoint_1",
weightsRoot / "checkpoint_2",
weightsRoot / "checkpoint_3"]
# Sort checkpoints newest-first by modification time
var existing: seq[tuple[mtime: Time, path: string]]
for p in checkpoints:
if dirExists(p):
existing.add((getLastModificationTime(p), p))
existing.sort(proc(a, b: tuple[mtime: Time, path: string]): int =
cmp(b.mtime, a.mtime)) # descending
let candidates = @[weightsRoot / "latest"] & existing.mapIt(it.path)
for candidate in candidates:
if dirExists(candidate):
var ok = true
for f in weightFiles: