Roll Up Ball¶
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 RoboWits 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✗ 11m 6% | 09-26 10:39 | 11m | 29 | 1.3M / 15k | $0.026 | deterministic 1, grader_error 0, instance_exact 0, instance_ok 1, n_actions 472, video_rendered 1 |
| L✗ 1h 26m | 09-29 19:16 | 1h 26m | 166 | 22.3M / 155k | $0.330 | deterministic 1, grader_error 0, live_success 0, n_actions 5918, replay_success 0, video_rendered 1 |
Task instruction (upstream)
Move the box into the basket.
Playback speed
What RoboWits states about this task
| Success criteria | 1. Box is completely inside the basket's bounding box 2. Box and basket are on the table |
| Objects | box high basket long board |
| Physics | rigid |
| Episode budget | 200 control steps |
| Default control mode | EE_ABS |
| Evaluation scenes | 50 |
| Published mutations | 8 |
| BlenderKit assets | 2 (not redistributable — mounted from the host) |
| Registry id | robowits/05-roll-up-ball-v0 |
| Environment class | RollUpBallEnv |
| Defined in | gs_gym/envs/robowits/05_roll_up_ball.py |
From https://github.com/UMass-Embodied-AGI/RoboWits @ 9cc30ae.
Tags¶
Task DomainManipulation
Why this task is interesting¶
Not yet written.
Capability notes¶
Not yet written.
Oracle demo review¶
Not yet reviewed.