jalf/TIR_PROJ
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Checkpoint 4

Browse Source
This commit is contained in:
Johnny Fernandes
2026-05-11 00:42:52 +01:00
parent 2a6db038df
commit 6688325d89
26 changed files with 2018 additions and 503 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/run_webots.sh
+14 -9
View File
@@ -7,29 +7,33 @@
# Usage:
# tools/run_webots.sh [N] [MODE]
# N : number of active sheep (1..10), default 10
# MODE : "rl" | "strombom" | "sequential", default "rl"
# MODE : "bc" | "rl" | "strombom" | "sequential" | "dagger", default "bc"
#
# Examples:
# tools/run_webots.sh 10 rl # BC-trained RL policy, 10 sheep
# tools/run_webots.sh 10 bc # BC-trained policy, 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
#
# Notes:
# * The RL mode loads training/runs/bc_solo/policy.zip by default.
# Override via HERDING_POLICY_DIR=/path/to/run env var.
# * The RL mode loads the latest BC policy by default — priority
# bc_dagger_v2 → bc_dagger → bc_c2v3 (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).
set -e
N=${1:-10}
MODE=${2:-rl}
MODE=${2:-bc}
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 '$MODE'" >&2; exit 1 ;;
bc|rl|strombom|sequential|dagger) ;;
*) echo "MODE must be bc|rl|strombom|sequential|dagger, got '$MODE'" >&2; exit 1 ;;
esac
DAGGER_DRIVER=${HERDING_DAGGER_DRIVER:-teacher}
ROOT="$( cd "$( dirname "${BASH_SOURCE[0]}" )/.." && pwd )"
SRC="$ROOT/worlds/field.wbt"
@@ -46,15 +50,16 @@ echo "------------------------------------------------------------"
echo "World : $DST"
echo "Mode : $MODE"
echo "Sheep : $active active"
echo "Policy dir : ${HERDING_POLICY_DIR:-$ROOT/training/runs/bc_solo}"
echo "Policy dir : ${HERDING_POLICY_DIR:-$ROOT/training/runs/bc_v3}"
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_solo}"
RESOLVED_POLICY_DIR="${HERDING_POLICY_DIR:-$ROOT/training/runs/bc_v3}"
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"