29 lines
844 B
Bash
29 lines
844 B
Bash
#!/bin/bash
|
|
# scripts/hpc/train.pbs — Submit PPO training as a batch job with qsub.
|
|
#
|
|
# Usage (from project root):
|
|
# qsub scripts/hpc/train.pbs
|
|
#
|
|
# To target a specific GPU cluster (default: joltik):
|
|
# module swap cluster/accelgor && qsub scripts/hpc/train.pbs
|
|
|
|
#PBS -N brittlestar-ppo
|
|
#PBS -l nodes=1:ppn=8:gpus=1
|
|
#PBS -l walltime=24:00:00
|
|
#PBS -l mem=32gb
|
|
#PBS -o runs/pbs_${PBS_JOBID}.out
|
|
#PBS -e runs/pbs_${PBS_JOBID}.err
|
|
|
|
set -euo pipefail
|
|
|
|
cd "$PBS_O_WORKDIR"
|
|
|
|
module load vsc-venv
|
|
source vsc-venv --activate --modules env/hpc/modules.txt
|
|
|
|
# EGL is required for headless MuJoCo operation — both for the physics
|
|
# simulation loop and for rendering videos to disk. Without this, MuJoCo
|
|
# attempts to open an X11 display and fails on compute nodes.
|
|
export MUJOCO_GL=egl
|
|
|
|
python src/train.py --config configs/production_training.yaml
|