Checkpoint 5 - incomplete

tools/run_webots.sh

@@ -17,7 +17,7 @@
 #
 # Notes:
 # * The RL mode loads the latest BC policy by default — priority
-#   bc_dagger_v2 → bc_dagger → bc_c2v3 (the controller resolves it).
+#   the BC policy (bc/policy.zip) (the controller resolves it).
 #   (LiDAR-perception, frame-stack K=4). Override via
 #   HERDING_POLICY_DIR=/path/to/run env var.
 # * Conda env "tir" must be active (provides stable-baselines3 + torch).
@@ -50,12 +50,12 @@ echo "------------------------------------------------------------"
 echo "World      : $DST"
 echo "Mode       : $MODE"
 echo "Sheep      : $active active"
-echo "Policy dir : ${HERDING_POLICY_DIR:-$ROOT/training/runs/bc_v3}"
+echo "Policy dir : ${HERDING_POLICY_DIR:-$ROOT/training/runs/bc}"
 echo "------------------------------------------------------------"
 
 # Webots strips HERDING_* env vars from controller subprocesses in some
 # setups, so we also write a runtime config file the controller reads.
-RESOLVED_POLICY_DIR="${HERDING_POLICY_DIR:-$ROOT/training/runs/bc_v3}"
+RESOLVED_POLICY_DIR="${HERDING_POLICY_DIR:-$ROOT/training/runs/bc}"
 cat > "$ROOT/herding_runtime.cfg" <<EOF
 HERDING_MODE=$MODE
 HERDING_POLICY_DIR=$RESOLVED_POLICY_DIR
@@ -65,4 +65,32 @@ EOF
 export HERDING_MODE="$MODE"
 export HERDING_POLICY_DIR="$RESOLVED_POLICY_DIR"
 
-exec webots "$DST"
+# The controller writes this sentinel when all GT sheep are penned. We
+# poll for it and kill Webots so the run finishes cleanly instead of
+# idling for minutes after the task is done.
+DONE_FILE="$ROOT/training/dagger/.DONE"
+mkdir -p "$(dirname "$DONE_FILE")"
+rm -f "$DONE_FILE"
+
+webots "$DST" &
+WEBOTS_PID=$!
+
+cleanup() {
+    kill "$WEBOTS_PID" 2>/dev/null || true
+    wait "$WEBOTS_PID" 2>/dev/null || true
+    exit 0
+}
+trap cleanup INT TERM
+
+# Poll for the sentinel; bail when Webots exits on its own or when the
+# user closes the window.
+while kill -0 "$WEBOTS_PID" 2>/dev/null; do
+    if [[ -f "$DONE_FILE" ]]; then
+        echo "[run_webots] all sheep penned — closing Webots"
+        sleep 1                       # let the controller print its line
+        kill "$WEBOTS_PID" 2>/dev/null || true
+        break
+    fi
+    sleep 1
+done
+wait "$WEBOTS_PID" 2>/dev/null || true