From 169d4dcb144f5c65b8b83dce9f50827e173fd392 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=EC=A0=95=EC=8B=9C=EC=9B=90?= <sebastianrcnt@gmail.com>
Date: Mon, 11 May 2026 05:53:54 +0900
Subject: [PATCH] Cycle 1: c_puct 3->5, dirichlet_eps 0.25->0.4 produced first
 natural-end wins

50-iter sweep on default.yaml with stronger MCTS exploration:
- c_puct: 3.0 -> 5.0 (UCB weight, more exploration of low-prior actions)
- root_dirichlet_epsilon: 0.25 -> 0.4 (more noise injected at root prior)

Standalone eval at iter 50 (30 games/opponent, all natural-end, timeouts=0):
- vs heuristic-balanced:    W=0/30 S=-70.5  (PA 0.15)
- vs heuristic-aggressive:  W=2/30 S=-65.1  (PA 0.14)  [+10, +4]
- vs heuristic-cautious:    W=1/30 S=-48.0  (PA 0.14)  [+2]

3 natural-end wins vs prev trapfix baseline iter 44 (which had 0 natural
wins + 1 timeout-tie). Stall trap fixed remains true (timeouts=0 in c1).

Trade-off observed: more exploration -> higher variance. Score avg vs
cautious worsened (-32 -> -48), but win events appeared. For the
non-terminal-win objective, exploration win > score-avg loss.

Next: commit to long run (300 iter) with these params before tuning more.
---
 configs/ismcts/default.yaml      |  4 ++--
 scripts/autonomous_cycle_eval.sh | 30 ++++++++++++++++++++++++++++++
 2 files changed, 32 insertions(+), 2 deletions(-)
 create mode 100755 scripts/autonomous_cycle_eval.sh

diff --git a/configs/ismcts/default.yaml b/configs/ismcts/default.yaml
index 798bdbf..a6b20bf 100644
--- a/configs/ismcts/default.yaml
+++ b/configs/ismcts/default.yaml
@@ -22,14 +22,14 @@ network:
   activation: relu
 mcts:
   n_simulations: 50
-  c_puct: 3.0
+  c_puct: 5.0
   max_depth: 200
   parallel_simulations: 64
   virtual_loss_value: 5.0
   eval_n_simulations: 16
   rollout_policy: heuristic_balanced
   root_dirichlet_alpha: 0.3
-  root_dirichlet_epsilon: 0.25
+  root_dirichlet_epsilon: 0.4
 temperature:
   training: 1.0
   eval: 0.0
diff --git a/scripts/autonomous_cycle_eval.sh b/scripts/autonomous_cycle_eval.sh
new file mode 100755
index 0000000..31c2e9c
--- /dev/null
+++ b/scripts/autonomous_cycle_eval.sh
@@ -0,0 +1,30 @@
+#!/bin/bash
+# Autonomous cycle eval helper.
+# Usage: ./autonomous_cycle_eval.sh <run-prefix> [extra eval args...]
+# Finds latest run matching prefix, runs eval --ckpt latest.pt with 30 games,
+# and reports: timeouts, natural-end wins per opponent.
+
+set -euo pipefail
+
+PREFIX="${1:-}"
+shift || true
+
+if [ -z "$PREFIX" ]; then
+    echo "usage: $0 <run-prefix> [extra eval args...]"
+    exit 1
+fi
+
+RUN=$(ls -td runs/*${PREFIX}* 2>/dev/null | head -1)
+if [ -z "$RUN" ]; then
+    echo "no run matching ${PREFIX}" >&2
+    exit 1
+fi
+
+CKPT="$RUN/latest.pt"
+if [ ! -f "$CKPT" ]; then
+    echo "no checkpoint at $CKPT" >&2
+    exit 1
+fi
+
+echo "=== eval $CKPT ==="
+uv run lost-cities-ismcts eval --ckpt "$CKPT" --games 30 --verbose "$@" 2>&1