Dishes In Bin¶
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✗ 1h 30m 0% | 09-27 07:18 | 1h 30m | 194 | 25.7M / 111k | $0.370 | deterministic 1, grader_error 0, instance_exact 1, instance_ok 1, n_actions 986, video_rendered 1 |
| L✗ 1h 30m | 09-29 03:35 | 1h 30m | 263 | 35.2M / 114k | $0.443 | deterministic 0, grader_error 0, live_success 0, n_actions 13533, replay_success 0, video_rendered 0 |
Task instruction (upstream)
Put the dishware in the grey bin
No oracle video published upstream — this is the scene it starts from.
What RoboLab states about this task
| Success predicate | object_in_container |
| Predicate arguments | object: ['mug', 'mug_01', 'bowl'] · container: grey_bin · logical: all · require_gripper_detached: True |
| Scored subtasks | 1 |
| Subtask predicates | pick_and_place |
| Objects | mug mug_01 bowl grey_bin banana_near banana_far rubiks_cube_top rubiks_cube_middle rubiks_cube_bottom ketchup_bottle |
| Upstream attributes | vague semantics |
| Upstream difficulty | simple |
| Episode budget | 180 s |
| Other wordings | vague — Put away dishes specific — Pick up the two mugs and a bowl from the table and place them into the grey bin |
| Environment class | DishesInBinTask |
| Upstream name | DishesInBinTask |
| Defined in | robolab/tasks/benchmark/dishes_in_bin.py |
From https://github.com/NVlabs/RoboLab @ v0.3.1.
Tags¶
Task DomainManipulation
Skill primitives in the demo: semanticsvague
Why this task is interesting¶
Not yet written.
Capability notes¶
Not yet written.
Oracle demo review¶
Not yet reviewed.