From e9e7cbbbdaaa6e8e0be7abdbc6e3bcad2b1730a5 Mon Sep 17 00:00:00 2001 From: Pepijn Date: Fri, 17 Apr 2026 13:34:01 +0100 Subject: [PATCH] ci(robocasa): smoke-eval 10 atomic tasks instead of 1 Broader coverage in the benchmark CI job: evaluate SmolVLA on ten fixture-centric atomic RoboCasa tasks (one episode each) instead of just CloseFridge. The tasks are all drawn from TARGET_TASKS.atomic_seen and selected to avoid object-manipulation categories that would require the objaverse/aigen asset packs (we only ship objs_lw in the Docker image, paired with obj_registries=["lightwheel"] on the runtime side). Tasks: CloseFridge, OpenCabinet, OpenDrawer, TurnOnMicrowave, TurnOffStove, CloseToasterOvenDoor, SlideDishwasherRack, TurnOnSinkFaucet, NavigateKitchen, TurnOnElectricKettle. `scripts/ci/parse_eval_metrics.py` already handles multi-task output via the `overall` key, so no parser changes needed. Bumped the metrics artifact's task label to `atomic_smoke_10` to reflect the grouping. Made-with: Cursor --- .github/workflows/benchmark_tests.yml | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/.github/workflows/benchmark_tests.yml b/.github/workflows/benchmark_tests.yml index 83da814e3..8bf788c20 100644 --- a/.github/workflows/benchmark_tests.yml +++ b/.github/workflows/benchmark_tests.yml @@ -346,7 +346,7 @@ jobs: load: true tags: lerobot-benchmark-robocasa:ci - - name: Run RoboCasa365 smoke eval (1 episode) + - name: Run RoboCasa365 smoke eval (10 atomic tasks, 1 episode each) if: env.HF_USER_TOKEN != '' run: | docker run --name robocasa-eval --gpus all \ @@ -361,7 +361,7 @@ jobs: lerobot-eval \ --policy.path=lerobot/smolvla_robocasa \ --env.type=robocasa \ - --env.task=CloseFridge \ + --env.task=CloseFridge,OpenCabinet,OpenDrawer,TurnOnMicrowave,TurnOffStove,CloseToasterOvenDoor,SlideDishwasherRack,TurnOnSinkFaucet,NavigateKitchen,TurnOnElectricKettle \ --eval.batch_size=1 \ --eval.n_episodes=1 \ --eval.use_async_envs=false \ @@ -383,7 +383,7 @@ jobs: python3 scripts/ci/parse_eval_metrics.py \ --artifacts-dir /tmp/robocasa-artifacts \ --env robocasa \ - --task CloseFridge \ + --task atomic_smoke_10 \ --policy lerobot/smolvla_robocasa - name: Upload RoboCasa365 rollout video