3D replay: the models' plans only

README.md

@@ -24,7 +24,7 @@ tasks on other days.
 |---|---|
 | `/web` | OpenEnv's web UI. **Explore**: the eval explorer, the 3D replay and the train graph. **Playground**: reset, step and the MCP tools by hand |
 | `/explorer/` | the leaderboard and every model's plan on every eval task; pick one to watch it |
-| `/twin/` | the 3D replay: any plan on the line's real track from OpenStreetMap, signals, level crossings, closures, the train graph and the cost as it accrues |
+| `/twin/` | the 3D replay: each model's plan on every eval task, on the line's real track from OpenStreetMap, with signals, level crossings, closures, the train graph and the cost as it accrues |
 | `/viewer/` | the train graph (time across, distance down) of any plan, with the plan's holds, short-turns and rule breaks |
 | `/reset`, `/step`, `/state`, `/ws`, `/mcp` | OpenEnv |
 | `/rail_ops/...` | OpenEnv Task API (`splits`, `num_tasks`, `task`, `task_range`) |

openenv/rail_openenv/web/explorer/index.html

@@ -220,7 +220,7 @@ function renderGrid() {
     }).join("");
     return `<tr><td class="task"><b>${esc(day(r.t.day))}</b> ${esc(r.t.start)}–${esc(r.t.end)} <span class="tier">${esc(TIER[r.t.difficulty] || r.t.difficulty)}</span><br><small>${esc(cause)}</small></td>`
       + `<td class="n">${r.t.runs}</td>${cells}<td class="n">${f3(r.mean)}</td>`
-      + `<td><a href="/twin/?task=${encodeURIComponent(r.id)}&plan=optimal">3D</a> · <a href="/viewer/?task=${encodeURIComponent(r.id)}&plan=optimal">graph</a></td></tr>`;
+      + `<td><a href="/twin/?task=${encodeURIComponent(r.id)}">3D</a> · <a href="/viewer/?task=${encodeURIComponent(r.id)}&plan=optimal">graph</a></td></tr>`;
   }).join("");
   $("#grid").innerHTML = head + `<tbody>${body}</tbody>`;
   for (const h of $("#grid").querySelectorAll("th.sort")) h.onclick = () => {

openenv/rail_openenv/web/twin/app.js

@@ -162,11 +162,14 @@ function seek(t) {
 
 // --- loading a task and a plan ----------------------------------------------------------------------------
 
+// the replay shows the models' plans (the eval runs) and live episodes on this server, not the reference methods
+// (the CP-SAT optimum, the greedy dispatchers, change nothing); a server without model runs offers everything
 async function loadPlans(taskId, want) {
-  const plans = await json(`/api/tasks/${encodeURIComponent(taskId)}/plans`);
+  const all = await json(`/api/tasks/${encodeURIComponent(taskId)}/plans`);
+  const models = all.filter((p) => p.id.startsWith("run:") || p.id.startsWith("episode:"));
+  const plans = models.length ? models : all;
   $("#plan").innerHTML = plans.map((p) => `<option value="${p.id}">${p.label}${p.reward !== null && p.reward !== undefined ? ` · ${(+p.reward).toFixed(3)}` : ""}</option>`).join("");
-  const model = plans.find((p) => p.id.startsWith("run:"));
-  $("#plan").value = plans.some((p) => p.id === want) ? want : model ? model.id : "optimal";
+  $("#plan").value = plans.some((p) => p.id === want) ? want : plans[0].id;
 }
 
 async function loadReplay(keepTime) {
@@ -239,12 +242,13 @@ async function main() {
   $("#loadmsg").textContent = "OpenStreetMap: track, stations, buildings…";
   const [twin, tasks] = await Promise.all([loadTwin(), json("/api/tasks")]);
   TWIN = twin;
-  const label = (t) => `${t.day} ${t.start}–${t.end} · ${TIER[t.difficulty] || t.difficulty} · ${t.runs} trains${t.model_plans ? " · ★" : ""}`;
-  const group = (split) => tasks.filter((t) => t.split === split).sort((a, b) => (b.model_plans - a.model_plans) || a.task_id.localeCompare(b.task_id));
-  $("#task").innerHTML = ["eval", "train"].map((sp) => `<optgroup label="${sp === "eval" ? "Eval (★ has a model's plan)" : "Train"}">`
-    + group(sp).map((t) => `<option value="${t.task_id}">${label(t)}</option>`).join("") + "</optgroup>").join("");
+  const label = (t) => `${t.day} ${t.start}–${t.end} · ${TIER[t.difficulty] || t.difficulty} · ${t.runs} trains`;
+  // the eval tasks the models were run on; every task when this server has no model runs
+  const evals = tasks.filter((t) => t.split === "eval" && t.model_plans);
+  const shown = (evals.length ? evals : tasks).sort((a, b) => a.task_id.localeCompare(b.task_id));
+  $("#task").innerHTML = shown.map((t) => `<option value="${t.task_id}">${label(t)}</option>`).join("");
   const want = params.get("task");
-  $("#task").value = tasks.some((t) => t.task_id === want) ? want : tasks.some((t) => t.task_id === FEATURED) ? FEATURED : tasks[0].task_id;
+  $("#task").value = shown.some((t) => t.task_id === want) ? want : shown.some((t) => t.task_id === FEATURED) ? FEATURED : shown[0].task_id;
   $("#station").innerHTML += twin.stations.map((s) => `<option value="${s.code}">${s.name}</option>`).join("");
   graph = new TrainGraph($("#graph"), $("#gtip"), (t) => seek(t), (u) => select(u, false));
   cost = new CostChart($("#cost"), $("#ctip"), (t) => seek(t));