Fix WandB config issue and achieve working DPPO setup

- Disable WandB in dev script to avoid config object vs string error
- Successfully completed development test (Job 3445106)
- Confirmed: pre-training works, loss reduces, checkpoints save
- Update experiment tracking with successful results

slurm/run_dppo_dev.sh

@@ -41,11 +41,11 @@ echo "PyTorch version: $(python -c 'import torch; print(torch.__version__)')"
 echo "CUDA available: $(python -c 'import torch; print(torch.cuda.is_available())')"
 echo ""
 
-# Run a quick pre-training test with reduced epochs
+# Run a quick pre-training test with reduced epochs (disable WandB for dev test)
 python script/run.py --config-name=pre_diffusion_mlp \
     --config-dir=cfg/gym/pretrain/hopper-medium-v2 \
     train.n_epochs=2 \
     train.save_model_freq=1 \
-    wandb=${WANDB_MODE:-null}
+    wandb=null
 
 echo "Dev test completed!"