Checkpoint 6
This commit is contained in:
+9
-13
@@ -7,19 +7,17 @@
|
||||
# Usage:
|
||||
# tools/run_webots.sh [N] [MODE]
|
||||
# N : number of active sheep (1..10), default 10
|
||||
# MODE : "bc" | "rl" | "strombom" | "sequential" | "dagger", default "bc"
|
||||
# MODE : "bc" | "rl" | "strombom" | "sequential", default "bc"
|
||||
#
|
||||
# Examples:
|
||||
# tools/run_webots.sh 10 bc # BC-trained policy, 10 sheep
|
||||
# tools/run_webots.sh 10 bc # behaviour-cloned MLP, 10 sheep
|
||||
# tools/run_webots.sh 10 rl # KL-PPO fine-tune of bc, 10 sheep
|
||||
# tools/run_webots.sh 5 sequential # the analytic teacher, 5 sheep
|
||||
# tools/run_webots.sh 3 strombom # canonical baseline, 3 sheep
|
||||
# tools/run_webots.sh 5 sequential # single-target analytic baseline
|
||||
# tools/run_webots.sh 3 strombom # canonical Strömbom analytic
|
||||
#
|
||||
# Notes:
|
||||
# * The RL mode loads the latest BC policy by default — priority
|
||||
# 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.
|
||||
# * bc loads training/runs/bc/policy.zip, rl loads training/runs/rl.
|
||||
# Override via HERDING_POLICY_DIR=/path/to/run env var.
|
||||
# * Conda env "tir" must be active (provides stable-baselines3 + torch).
|
||||
|
||||
set -e
|
||||
@@ -30,10 +28,9 @@ if (( N < 1 || N > 10 )); then
|
||||
echo "N must be 1..10, got $N" >&2; exit 1
|
||||
fi
|
||||
case "$MODE" in
|
||||
bc|rl|strombom|sequential|dagger) ;;
|
||||
*) echo "MODE must be bc|rl|strombom|sequential|dagger, got '$MODE'" >&2; exit 1 ;;
|
||||
bc|rl|strombom|sequential) ;;
|
||||
*) echo "MODE must be bc|rl|strombom|sequential, got '$MODE'" >&2; exit 1 ;;
|
||||
esac
|
||||
DAGGER_DRIVER=${HERDING_DAGGER_DRIVER:-teacher}
|
||||
|
||||
ROOT="$( cd "$( dirname "${BASH_SOURCE[0]}" )/.." && pwd )"
|
||||
SRC="$ROOT/worlds/field.wbt"
|
||||
@@ -59,7 +56,6 @@ RESOLVED_POLICY_DIR="${HERDING_POLICY_DIR:-$ROOT/training/runs/bc}"
|
||||
cat > "$ROOT/herding_runtime.cfg" <<EOF
|
||||
HERDING_MODE=$MODE
|
||||
HERDING_POLICY_DIR=$RESOLVED_POLICY_DIR
|
||||
HERDING_DAGGER_DRIVER=$DAGGER_DRIVER
|
||||
EOF
|
||||
|
||||
export HERDING_MODE="$MODE"
|
||||
@@ -68,7 +64,7 @@ export HERDING_POLICY_DIR="$RESOLVED_POLICY_DIR"
|
||||
# The controller writes this sentinel when all GT sheep are penned. We
|
||||
# poll for it and kill Webots so the run finishes cleanly instead of
|
||||
# idling for minutes after the task is done.
|
||||
DONE_FILE="$ROOT/training/dagger/.DONE"
|
||||
DONE_FILE="$ROOT/training/.run_done"
|
||||
mkdir -p "$(dirname "$DONE_FILE")"
|
||||
rm -f "$DONE_FILE"
|
||||
|
||||
|
||||
Reference in New Issue
Block a user