feat: HoReKa cluster adaptation and validation

- Updated all WandB project names to use dppo- prefix for organization
- Added flexible dev testing script for all environments
- Created organized dev_tests directory for test scripts
- Fixed MuJoCo compilation issues (added GCC compiler flags)
- Documented Python 3.10 compatibility and Furniture-Bench limitation
- Validated pre-training for Gym, Robomimic, D3IL environments
- Updated experiment tracking with validation results
- Enhanced README with troubleshooting and setup instructions

slurm/dev_tests/test_d3il_avoid_m1.sh

@@ -0,0 +1,35 @@
+#!/bin/bash
+#SBATCH --job-name=dppo_d3il_test
+#SBATCH --account=hk-project-p0022232
+#SBATCH --partition=dev_accelerated
+#SBATCH --gres=gpu:1
+#SBATCH --nodes=1
+#SBATCH --ntasks-per-node=1
+#SBATCH --cpus-per-task=8
+#SBATCH --time=00:30:00
+#SBATCH --mem=24G
+#SBATCH --output=logs/dppo_d3il_%j.out
+#SBATCH --error=logs/dppo_d3il_%j.err
+
+# Load modules and set environment
+module load devel/cuda/12.4
+export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/lib/nvidia
+export CC=gcc
+export CXX=g++
+export WANDB_MODE=online
+export DPPO_WANDB_ENTITY=${DPPO_WANDB_ENTITY:-"dominik_roth"}
+export DPPO_DATA_DIR=${DPPO_DATA_DIR:-$SLURM_SUBMIT_DIR/data}
+export DPPO_LOG_DIR=${DPPO_LOG_DIR:-$SLURM_SUBMIT_DIR/log}
+
+cd $SLURM_SUBMIT_DIR
+source .venv/bin/activate
+
+echo "Testing D3IL avoid_m1 pretrain..."
+echo "Job ID: $SLURM_JOB_ID"
+
+python script/run.py --config-name=pre_diffusion_mlp \
+    --config-dir=cfg/d3il/pretrain/avoid_m1 \
+    train.n_epochs=2 \
+    train.save_model_freq=1
+
+echo "D3IL test completed!"

slurm/dev_tests/test_robomimic_lift.sh

@@ -0,0 +1,35 @@
+#!/bin/bash
+#SBATCH --job-name=dppo_robomimic_test
+#SBATCH --account=hk-project-p0022232
+#SBATCH --partition=dev_accelerated
+#SBATCH --gres=gpu:1
+#SBATCH --nodes=1
+#SBATCH --ntasks-per-node=1
+#SBATCH --cpus-per-task=8
+#SBATCH --time=00:30:00
+#SBATCH --mem=24G
+#SBATCH --output=logs/dppo_robomimic_%j.out
+#SBATCH --error=logs/dppo_robomimic_%j.err
+
+# Load modules and set environment
+module load devel/cuda/12.4
+export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/lib/nvidia
+export CC=gcc
+export CXX=g++
+export WANDB_MODE=online
+export DPPO_WANDB_ENTITY=${DPPO_WANDB_ENTITY:-"dominik_roth"}
+export DPPO_DATA_DIR=${DPPO_DATA_DIR:-$SLURM_SUBMIT_DIR/data}
+export DPPO_LOG_DIR=${DPPO_LOG_DIR:-$SLURM_SUBMIT_DIR/log}
+
+cd $SLURM_SUBMIT_DIR
+source .venv/bin/activate
+
+echo "Testing Robomimic lift pretrain..."
+echo "Job ID: $SLURM_JOB_ID"
+
+python script/run.py --config-name=pre_diffusion_mlp \
+    --config-dir=cfg/robomimic/pretrain/lift \
+    train.n_epochs=2 \
+    train.save_model_freq=1
+
+echo "Robomimic test completed!"

slurm/run_dppo_dev_flexible.sh

@@ -0,0 +1,100 @@
+#!/bin/bash
+#SBATCH --job-name=dppo_dev_test
+#SBATCH --account=hk-project-p0022232
+#SBATCH --partition=dev_accelerated
+#SBATCH --gres=gpu:1
+#SBATCH --nodes=1
+#SBATCH --ntasks-per-node=1
+#SBATCH --cpus-per-task=8
+#SBATCH --time=00:30:00
+#SBATCH --mem=24G
+#SBATCH --output=logs/dppo_dev_%j.out
+#SBATCH --error=logs/dppo_dev_%j.err
+
+# Usage: TASK=hopper MODE=pretrain sbatch slurm/run_dppo_dev_flexible.sh
+# Usage: TASK=hopper MODE=finetune sbatch slurm/run_dppo_dev_flexible.sh
+
+# Load required modules
+module load devel/cuda/12.4
+
+# Fix MuJoCo library path for fine-tuning
+export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/lib/nvidia
+
+# Use GCC instead of Intel compiler for MuJoCo compilation (Intel icx too strict)
+export CC=gcc
+export CXX=g++
+
+# Set environment variables for WandB
+export WANDB_MODE=online
+export DPPO_WANDB_ENTITY=${DPPO_WANDB_ENTITY:-"dominik_roth"}
+
+# Default paths
+export DPPO_DATA_DIR=${DPPO_DATA_DIR:-$SLURM_SUBMIT_DIR/data}
+export DPPO_LOG_DIR=${DPPO_LOG_DIR:-$SLURM_SUBMIT_DIR/log}
+
+# Set defaults if not provided
+TASK=${TASK:-hopper}
+MODE=${MODE:-pretrain}
+
+# Change to project directory
+cd $SLURM_SUBMIT_DIR
+
+# Activate virtual environment
+source .venv/bin/activate
+
+echo "Starting DPPO dev test..."
+echo "Job ID: $SLURM_JOB_ID"
+echo "Node: $SLURM_NODELIST"
+echo "Task: $TASK"
+echo "Mode: $MODE"
+echo "GPU: $CUDA_VISIBLE_DEVICES"
+echo ""
+echo "Python version: $(python --version)"
+echo "PyTorch version: $(python -c 'import torch; print(torch.__version__)')"
+echo "CUDA available: $(python -c 'import torch; print(torch.cuda.is_available())')"
+echo ""
+
+if [ "$MODE" = "pretrain" ]; then
+    echo "Running pre-training test (2 epochs)..."
+    
+    if [ "$TASK" = "hopper" ]; then
+        ENV_CONFIG="hopper-medium-v2"
+    elif [ "$TASK" = "walker2d" ]; then
+        ENV_CONFIG="walker2d-medium-v2"  
+    elif [ "$TASK" = "halfcheetah" ]; then
+        ENV_CONFIG="halfcheetah-medium-v2"
+    else
+        echo "Unknown task: $TASK"
+        exit 1
+    fi
+    
+    python script/run.py --config-name=pre_diffusion_mlp \
+        --config-dir=cfg/gym/pretrain/$ENV_CONFIG \
+        train.n_epochs=2 \
+        train.save_model_freq=1
+        
+elif [ "$MODE" = "finetune" ]; then
+    echo "Running fine-tuning test (short run)..."
+    
+    if [ "$TASK" = "hopper" ]; then
+        ENV_CONFIG="hopper-v2"
+    elif [ "$TASK" = "walker2d" ]; then
+        ENV_CONFIG="walker2d-v2"
+    elif [ "$TASK" = "halfcheetah" ]; then
+        ENV_CONFIG="halfcheetah-v2"
+    else
+        echo "Unknown task: $TASK"
+        exit 1
+    fi
+    
+    python script/run.py --config-name=ft_ppo_diffusion_mlp \
+        --config-dir=cfg/gym/finetune/$ENV_CONFIG \
+        train.n_train_itr=10 \
+        train.val_freq=5
+        
+else
+    echo "Unknown mode: $MODE. Use 'pretrain' or 'finetune'"
+    exit 1
+fi
+
+echo "Dev test completed!"