Fix WandB configuration for proper logging

- Configure DPPO_WANDB_ENTITY environment variable in dev script
- Update README with clear WandB setup instructions
- Remove wandb=null to enable logging when credentials are set

slurm/run_dppo_dev.sh

@@ -14,11 +14,12 @@
 # Load required modules
 module load devel/cuda/12.4
 
-# Set environment variables
+# Set environment variables for WandB
 export WANDB_MODE=online
 export WANDB_PROJECT=dppo_dev_test
-# export WANDB_API_KEY=<your_api_key>  # TODO: Set your API key
-# export WANDB_ENTITY=<your_entity>    # TODO: Set your entity (username or team)
+export DPPO_WANDB_ENTITY=${DPPO_WANDB_ENTITY:-"your_wandb_username"}  # TODO: Set your WandB username
+# TODO: Set your WandB API key as environment variable:
+# export WANDB_API_KEY=<your_api_key>
 
 # Default paths (can be overridden by environment)
 export DPPO_DATA_DIR=${DPPO_DATA_DIR:-$SLURM_SUBMIT_DIR/data}
@@ -41,11 +42,11 @@ 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 (disable WandB for dev test)
+# Run a quick pre-training test with reduced epochs
+# Note: Will only log to WandB if WANDB_API_KEY and DPPO_WANDB_ENTITY are properly set
 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=null
+    train.save_model_freq=1
 
 echo "Dev test completed!"