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