Update experiment plan with validation results and WandB URLs

- Complete validation status table with results for all environments
- Add WandB tracking URLs for completed fine-tuning runs
- Document technical fixes and current job queue status
- Add test scripts for remaining D3IL avoid_m3 and robomimic transport validation

slurm/dev_tests/test_d3il_avoid_m3_finetune.sh

@@ -0,0 +1,29 @@
+#!/bin/bash
+#SBATCH --job-name=dppo_d3il_avoid_m3_ft
+#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=16G
+#SBATCH --output=logs/dppo_d3il_avoid_m3_ft_%j.out
+#SBATCH --error=logs/dppo_d3il_avoid_m3_ft_%j.err
+
+module load devel/cuda/12.4
+
+# Environment variables
+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_m3 fine-tuning..."
+python script/run.py --config-name=ft_ppo_diffusion_mlp \
+    --config-dir=cfg/d3il/finetune/avoid_m3 \
+    train.n_train_itr=50 \
+    train.save_model_freq=25

slurm/dev_tests/test_robomimic_transport_finetune.sh

@@ -0,0 +1,38 @@
+#!/bin/bash
+#SBATCH --job-name=dppo_transport_ft
+#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_transport_ft_%j.out
+#SBATCH --error=logs/dppo_transport_ft_%j.err
+
+module load devel/cuda/12.4
+
+# MuJoCo environment for fine-tuning
+export MUJOCO_PY_MUJOCO_PATH=$HOME/.mujoco/mujoco210
+export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:$HOME/.mujoco/mujoco210/bin:/usr/lib/nvidia
+export MUJOCO_GL=egl
+
+# Environment variables
+export WANDB_MODE=online
+export DPPO_WANDB_ENTITY=${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
+
+# Apply HoReKa MuJoCo compilation fix
+echo "Applying HoReKa MuJoCo compilation fix..."
+python -c "exec(open('fix_mujoco_compilation.py').read()); apply_mujoco_fix(); import mujoco_py; print('MuJoCo ready!')"
+
+echo "Testing robomimic transport fine-tuning..."
+python script/run.py --config-name=ft_ppo_diffusion_mlp \
+    --config-dir=cfg/robomimic/finetune/transport \
+    train.n_train_itr=50 \
+    train.save_model_freq=25