137b9e80c9
- Add SLURM job scripts for ManiSkill and Brax environments - Add job submission helper script with environment validation - Update README with HoReKa installation and usage instructions - Create logs directory structure - Configure wandb integration (requires external API key setup)
52 lines
1.4 KiB
Bash
Executable File
52 lines
1.4 KiB
Bash
Executable File
#!/bin/bash
|
|
#SBATCH --job-name=reppo_maniskill
|
|
#SBATCH --account=hk-project-p0022232
|
|
#SBATCH --partition=accelerated
|
|
#SBATCH --gres=gpu:1
|
|
#SBATCH --nodes=1
|
|
#SBATCH --ntasks-per-node=1
|
|
#SBATCH --cpus-per-task=8
|
|
#SBATCH --time=08:00:00
|
|
#SBATCH --mem=32G
|
|
#SBATCH --output=logs/reppo_maniskill_%j.out
|
|
#SBATCH --error=logs/reppo_maniskill_%j.err
|
|
|
|
# Load required modules
|
|
module load devel/cuda/12.4
|
|
|
|
# Set environment variables
|
|
export WANDB_MODE=online
|
|
export WANDB_PROJECT=reppo_maniskill
|
|
|
|
# Change to project directory
|
|
cd /hkfs/home/project/hk-project-robolear/ys1087/Projects/reppo
|
|
|
|
# Activate virtual environment
|
|
source .venv/bin/activate
|
|
|
|
# Note: Ensure WANDB_API_KEY and WANDB_ENTITY are set before running
|
|
|
|
# Run REPPO with ManiSkill environment
|
|
echo "Starting REPPO training with ManiSkill..."
|
|
echo "Job ID: $SLURM_JOB_ID"
|
|
echo "Node: $SLURM_NODELIST"
|
|
echo "GPU: $CUDA_VISIBLE_DEVICES"
|
|
|
|
# Default environment: PickCube-v1 (can be overridden)
|
|
ENV_NAME=${ENV_NAME:-PickCube-v1}
|
|
EXPERIMENT_TYPE=${EXPERIMENT_TYPE:-mjx_dmc_medium_data}
|
|
|
|
echo "Environment: $ENV_NAME"
|
|
echo "Experiment type: $EXPERIMENT_TYPE"
|
|
|
|
# Run the experiment
|
|
python reppo_alg/jaxrl/reppo.py \
|
|
env=maniskill \
|
|
env_name=$ENV_NAME \
|
|
experiment_override=$EXPERIMENT_TYPE \
|
|
wandb.mode=online \
|
|
wandb.entity=${WANDB_ENTITY} \
|
|
wandb.project=$WANDB_PROJECT \
|
|
wandb.name="reppo_${ENV_NAME}_${EXPERIMENT_TYPE}_${SLURM_JOB_ID}"
|
|
|
|
echo "Training completed!" |