fix(SAC_LSTM_Bot): freeze mirror-twin via eval-mode gate in twin launcher
SACLSTM_EVAL_MODE=1 in SacTwin.sh suppresses all sendTrainingMsg traffic (lever-4 gate), so the twin never trains — not even in-RAM within a battle. Required now that the main bot's SACLSTM_SAVE_INTERVAL drops to 1 (v2 relaunch after checkpoint-cadence diagnosis): without the gate the twin would persist per-battle drift and stop being the frozen reproducible opponent #54 specifies.
This commit is contained in:
@@ -46,6 +46,11 @@ cat > "$TARGET/SacTwin.sh" <<'EOF'
|
||||
DIR="$(cd "$(dirname "$0")" && pwd)"
|
||||
export SACLSTM_BOT_JSON="$DIR/SacTwin.json"
|
||||
export SACLSTM_WEIGHTS_PATH="$DIR/weights/sac_latest.zip"
|
||||
# Freeze contract (#54): the twin is a FROZEN sparring partner, not a
|
||||
# co-learner. Eval-mode gate (lever 4) suppresses all sendTrainingMsg traffic,
|
||||
# so the twin never trains — not even in-RAM within a battle. Without this,
|
||||
# any main-bot checkpoint-interval change would let twin drift accumulate.
|
||||
export SACLSTM_EVAL_MODE=1
|
||||
exec "$DIR/SAC_LSTM_Bot"
|
||||
EOF
|
||||
chmod +x "$TARGET/SacTwin.sh" "$TARGET/SAC_LSTM_Bot"
|
||||
|
||||
Reference in New Issue
Block a user