diff --git a/tools/training_runner/run.sh b/tools/training_runner/run.sh
index c4c611a..15a40a1 100755
--- a/tools/training_runner/run.sh
+++ b/tools/training_runner/run.sh
@@ -79,8 +79,13 @@ while true; do
     sleep 2
   fi
 
-  echo ">>> Running $remaining rounds (opponent: $OPPONENT)..."
-  java -cp ".:$JAR" RunTraining "$OPPONENT" "$remaining" && break || {
+  # ponytail: cap each battle at 60 rounds — matches the certified config.
+  # Round-end reward is cumulative totalScore/50; long battles grow it unboundedly
+  # and blow up the critic's value scale (seen at round 3160, vLoss 25745 by 3871).
+  # Short battles bound the reward, and fresh-process restarts clear thread state.
+  battle_rounds=$(( remaining > 60 ? 60 : remaining ))
+  echo ">>> Running $battle_rounds rounds (opponent: $OPPONENT)..."
+  java -cp ".:$JAR" RunTraining "$OPPONENT" "$battle_rounds" && break || {
     exit_code=$?
     echo ">>> Java runner exited with code $exit_code — checking if done..."
     remaining=$(remaining_rounds)