eval command added

models/README.md

@@ -18,4 +18,14 @@ To train ACT:
     --seed 0
 
 
-To evaluate the policy, run the same command but add ``--eval``. This loads the best validation checkpoint.
+To evaluate the policy, run the same command but add ``--eval``. This loads the best validation checkpoint.
+
+
+to eval: 
+
+mjpython model_eval.py \
+    --task_name sim_aloha_close_dishwasher \
+    --ckpt_dir ./ckpt_dir \
+    --policy_class ACT --kl_weight 10 --chunk_size 100 --hidden_dim 512 --batch_size 8 --dim_feedforward 3200 \
+    --num_epochs 2000  --lr 1e-5 \
+    --seed 0 --eval