Checkpoint 5 - incomplete

tools/auto_dagger.sh

@@ -16,7 +16,7 @@
 #
 # Env-var overrides:
 #   HERDING_POLICY_DIR : policy the controller loads (only used when
-#                        HERDING_DAGGER_DRIVER=student). Default bc_v3.
+#                        HERDING_DAGGER_DRIVER=student). Default bc.
 #   HERDING_DAGGER_DRIVER : "teacher" (default) or "student".
 #   HEADLESS=1          : force --no-rendering (default on).
 #   FLOCKS="1 3 5 8 10" : space-separated flock sizes to iterate over.
@@ -37,7 +37,7 @@ HEADLESS=${HEADLESS:-1}
 ROOT="$( cd "$( dirname "${BASH_SOURCE[0]}" )/.." && pwd )"
 SRC="$ROOT/worlds/field.wbt"
 DST="$ROOT/worlds/field_test.wbt"
-POLICY_DIR="${HERDING_POLICY_DIR:-$ROOT/training/runs/bc_v3}"
+POLICY_DIR="${HERDING_POLICY_DIR:-$ROOT/training/runs/bc}"
 DRIVER="${HERDING_DAGGER_DRIVER:-teacher}"
 DONE_FILE="$ROOT/training/dagger/.DONE"
 WEBOTS_PID=""

tools/dagger_merge_train.py

@@ -10,7 +10,7 @@ where:
 * ``actions`` is the **active-scan-teacher action computed from
   ground-truth sheep positions** (read off the sheep emitter).
 
-Combined with the existing sim demos (``training/demos_v3.npz`` by
+Combined with the existing sim demos (``training/demos.npz`` by
 default), this gives the BC student a training set that includes the
 real Webots false-positive distribution — closing the sim-to-real
 perception gap that the all-sim pipeline couldn't bridge.
@@ -19,7 +19,7 @@ Usage::
 
     # Iteration 1 — merge all dagger files with sim demos, retrain
     python -m tools.dagger_merge_train \\
-        --sim training/demos_v3.npz \\
+        --sim training/demos.npz \\
         --out training/runs/bc_dagger1
 
     # Iteration 2 — drop the sim baseline, train only on Webots data
@@ -48,7 +48,7 @@ import numpy as np
 
 def main() -> None:
     parser = argparse.ArgumentParser()
-    parser.add_argument("--sim", default="training/demos_v3.npz",
+    parser.add_argument("--sim", default="training/demos.npz",
                         help="Sim demo file to mix with the Webots data. "
                              "Pass --no-sim to train only on dagger data.")
     parser.add_argument("--no-sim", action="store_true",

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