Checkpoint 2

2026-05-07 22:00:10 +01:00
parent 90aa3bbcb4
commit 1bb9415414
37 changed files with 3068 additions and 2912 deletions
@@ -0,0 +1,63 @@
+#!/bin/bash
+# Launch Webots with N sheep enabled and the chosen controller mode.
+# Generates a temporary world file in worlds/field_test.wbt with sheep
+# beyond N commented out, sets the env vars the dog controller reads,
+# then execs Webots on it.
+#
+# Usage:
+#   tools/run_webots.sh [N] [MODE]
+#     N    : number of active sheep (1..10), default 10
+#     MODE : "rl" | "strombom" | "sequential", default "rl"
+#
+# Examples:
+#   tools/run_webots.sh 10 rl         # BC-trained RL policy, 10 sheep
+#   tools/run_webots.sh 5 sequential  # the analytic teacher, 5 sheep
+#   tools/run_webots.sh 3 strombom    # canonical baseline, 3 sheep
+#
+# Notes:
+# * The RL mode loads training/runs/bc_pretrained/policy.zip by default.
+#   Override via HERDING_POLICY_DIR=/path/to/run env var.
+# * Conda env "tir" must be active (provides stable-baselines3 + torch).
+
+set -e
+N=${1:-10}
+MODE=${2:-rl}
+
+if (( N < 1 || N > 10 )); then
+    echo "N must be 1..10, got $N" >&2; exit 1
+fi
+case "$MODE" in
+    rl|strombom|sequential) ;;
+    *) echo "MODE must be rl|strombom|sequential, got '$MODE'" >&2; exit 1 ;;
+esac
+
+ROOT="$( cd "$( dirname "${BASH_SOURCE[0]}" )/.." && pwd )"
+SRC="$ROOT/worlds/field.wbt"
+DST="$ROOT/worlds/field_test.wbt"
+
+cp "$SRC" "$DST"
+# Comment out sheep N+1..10 by prefixing the matching Sheep { ... } line.
+for i in $(seq $((N+1)) 10); do
+    sed -i "s|^Sheep .* \"sheep${i}\".*|# &|" "$DST"
+done
+
+active=$(grep -c '^Sheep' "$DST")
+echo "------------------------------------------------------------"
+echo "World      : $DST"
+echo "Mode       : $MODE"
+echo "Sheep      : $active active"
+echo "Policy dir : ${HERDING_POLICY_DIR:-$ROOT/training/runs/bc_pretrained}"
+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_pretrained}"
+cat > "$ROOT/herding_runtime.cfg" <<EOF
+HERDING_MODE=$MODE
+HERDING_POLICY_DIR=$RESOLVED_POLICY_DIR
+EOF
+
+export HERDING_MODE="$MODE"
+export HERDING_POLICY_DIR="$RESOLVED_POLICY_DIR"
+
+exec webots "$DST"