Stack Yellow On Red¶
Agent runs
Each mode of this task runs once per run. Est. cost is tokens at list price (data/prices.yml), never a bill; see the RoboLab runs for every task of a run.
Codex + GPT-6 Luna, reasoning xhigh (ChatGPT login)default run
| Trial | Started | Agent time | Model requests | Tokens in / out | Est. cost | Grade |
|---|---|---|---|---|---|---|
| U✓ 15m | 09-27 12:25 | 15m | 39 | 1.5M / 14k | $0.029 | deterministic 1, grader_error 0, instance_exact 1, instance_ok 1, n_actions 371, video_rendered 1 |
| L✓ 20m | 09-29 06:48 | 20m | 48 | 2.6M / 42k | $0.057 | deterministic 1, grader_error 0, live_success 1, n_actions 136, replay_success 1, video_rendered 1 |
Task instruction (upstream)
Stack the yellow block on the red block
No oracle video published upstream — this is the scene it starts from.
What RoboLab states about this task
| Success predicate | stacked |
| Predicate arguments | objects: ['red_block', 'yellow_block'] · order: bottom_to_top |
| Scored subtasks | 1 |
| Subtask predicates | Subtask |
| Objects | rubiks_cube rubiks_cube_1 rubiks_cube_2 grey_bin lizard_figurine birdhouse yellow_block red_block green_block blue_block lizard_figurine_01 |
| Upstream attributes | stacking |
| Upstream difficulty | simple |
| Episode budget | 60 s |
| Other wordings | vague — Stack blocks: yellow on red specific — Pick up the yellow block on the left and place it precisely on top of the red block in front of the birdhouse |
| Environment class | StackYellowOnRedTask |
| Upstream name | StackYellowOnRedTask |
| Defined in | robolab/tasks/benchmark/stack_yellow_on_red.py |
From https://github.com/NVlabs/RoboLab @ v0.3.1.
Tags¶
Task DomainManipulation
Skill primitives in the demo: stacking
Why this task is interesting¶
Not yet written.
Capability notes¶
Not yet written.
Oracle demo review¶
Not yet reviewed.