Fixed training of three models

train.sh

@@ -0,0 +1,23 @@
+#!/bin/bash
+
+set -euo pipefail
+
+# Override with DEVICE=... ./train.sh if you want to force a specific device.
+DEVICE="${DEVICE:-$(python -c 'import torch; print("cuda" if torch.cuda.is_available() else "cpu")')}"
+OUTPUT_CHECKPOINT="${OUTPUT_CHECKPOINT:-easy.pth}"
+
+# Example heavier runs:
+DEVICE=cuda python run.py train --checkpoint hard.pth --arena-compare-games 4 --arena-compare-simulations 4 --num-simulations 25
+DEVICE=cuda python run.py train --checkpoint medium.pth --arena-compare-games 3 --arena-compare-simulations 4 --num-simulations 20 --epochs 5 --num-eps 15 --num-iters 30
+python run.py train \
+  --checkpoint "$OUTPUT_CHECKPOINT" \
+  --arena-compare-games 0 \
+  --arena-compare-simulations 2 \
+  --device "$DEVICE" \
+  --num-simulations 20 \
+  --epochs 3 \
+  --num-eps 10 \
+  --num-iters 15 \
+  "$@"
+
+echo "Training finished!"