Full retrain pipeline + hybrid policy set

Ran end-to-end clean retrain + gym eval + 24-cell Webots sweep
(tools/full_pipeline.sh). Results:

  Differential — all 16 cells pen N/N. Updated policies committed.
  Mecanum     — new training stochastically regressed (only 2/8 cells
                vs the v2 baseline's 4/8). v2 baseline mec policies
                are RESTORED in this commit (training/runs/{bc,rl}_
                mecanum_*) — they remain the deliverable.

The retrain pipeline itself is committed for reproducibility
(tools/full_pipeline.sh: clean → train_all → eval_all → 24-cell
Webots sweep). The v2 mec policies are also backed up locally to
_backup_pretrain/mec_v2_baseline/ (gitignored).

Verified after restore:
  bc mec field_round n=10 → 10/10 in 147 s sim
  rl diff field n=5      → 5/5  in 137 s sim

tools/full_pipeline.sh

@@ -0,0 +1,86 @@
+#!/usr/bin/env bash
+# Full retrain + eval + Webots-validate pipeline.
+#
+# Usage:  bash tools/full_pipeline.sh
+#
+# Output logs are written to the repo root:
+#   full_pipeline.log    — main pipeline log
+#   stage_train.log      — make train_all output
+#   stage_eval.log       — make eval_all output
+#   stage_webots.log     — Webots validation sweep
+#
+# Total runtime estimate: 8–12 hours.
+
+set -e
+ROOT="$( cd "$( dirname "${BASH_SOURCE[0]}" )/.." && pwd )"
+cd "$ROOT"
+source "$ROOT/tools/setup_env.sh"
+
+PIPELINE_LOG="$ROOT/full_pipeline.log"
+TRAIN_LOG="$ROOT/stage_train.log"
+EVAL_LOG="$ROOT/stage_eval.log"
+WEBOTS_LOG="$ROOT/stage_webots.log"
+truncate -s 0 "$PIPELINE_LOG" "$TRAIN_LOG" "$EVAL_LOG" "$WEBOTS_LOG"
+
+log() { echo "[pipeline $(date +%H:%M:%S)] $*" | tee -a "$PIPELINE_LOG"; }
+
+log "=== START full pipeline $(date) ==="
+log ""
+log "Phase 1/4: clean_all"
+make clean_all 2>&1 | tee -a "$PIPELINE_LOG"
+log ""
+
+log "Phase 2/4: train_all (4 combos, ~8h)"
+make train_all 2>&1 | tee -a "$TRAIN_LOG"
+log "  train_all finished"
+log ""
+
+log "Phase 3/4: eval_all (gym eval, ~30min)"
+make eval_all 2>&1 | tee -a "$EVAL_LOG"
+log "  eval_all finished"
+log ""
+
+log "Phase 4/4: Webots validation sweep (~90min)"
+truncate -s 0 "$WEBOTS_LOG"
+
+run_cell() {
+    local MODE="$1" DRIVE="$2" WORLD="$3" N="$4"
+    echo "" | tee -a "$WEBOTS_LOG"
+    echo "=== $MODE $DRIVE $WORLD n=$N ===" | tee -a "$WEBOTS_LOG"
+    rm -f "$ROOT/training/.run_done"
+    local STDOUT="$ROOT/pipeline_${MODE}_${DRIVE}_${WORLD}_n${N}.stdout"
+    timeout --kill-after=15s 320 \
+    xvfb-run -a \
+    env WEBOTS_HEADLESS=1 WEBOTS_EXTRA_ARGS="--stdout --stderr" \
+        HERDING_SEED=42 \
+    bash tools/run_webots.sh "$N" "$MODE" "$DRIVE" "$WORLD" > "$STDOUT" 2>&1 || true
+    BEST=$(grep "GT_penned=" "$STDOUT" 2>/dev/null | awk -F'GT_penned=' '{print $2}' | awk '{split($1,a,"/"); print a[1]"/"a[2]}' | sort -t/ -k1,1n | tail -1)
+    grep -E "\[results\]" "$STDOUT" 2>/dev/null | head -1 | tee -a "$WEBOTS_LOG"
+    echo "  best GT_penned: $BEST" | tee -a "$WEBOTS_LOG"
+    pkill -9 -f "webots-bin|Xvfb" 2>/dev/null || true
+    sleep 1
+}
+
+# Differential drive: 4 controllers × 2 worlds × 2 n
+for M in bc rl strombom sequential; do
+  for W in field field_round; do
+    for N in 5 10; do
+      run_cell "$M" differential "$W" "$N"
+    done
+  done
+done
+
+# Mecanum drive: 2 controllers × 2 worlds × 2 n
+for M in bc rl; do
+  for W in field field_round; do
+    for N in 5 10; do
+      run_cell "$M" mecanum "$W" "$N"
+    done
+  done
+done
+
+log ""
+log "=== FULL PIPELINE DONE $(date) ==="
+log ""
+log "Summary:"
+grep -E "=== |best GT_penned" "$WEBOTS_LOG" | tee -a "$PIPELINE_LOG"