Aloha Single Peg Insertion¶
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 MuJoCo Playground (manipulation) 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 00m | 09-29 02:01 | 1h 00m | — | 7.5M / 183k | $0.193 | deterministic 1, grader_error 0, n_actions 995, video_rendered 1 |
| L✗ 55m | 09-29 02:27 | 55m | — | 17.7M / 129k | $0.284 | deterministic 1, grader_error 0, video_rendered 0 |
1 other run(s) of MuJoCo Playground (manipulation)
Codex + GPT-6 Luna, reasoning xhigh (Azure OpenAI API, 2026-09-30 stress test)
| Trial | Started | Agent time | Model requests | Tokens in / out | Est. cost | Grade |
|---|---|---|---|---|---|---|
| U✓ 8m | 09-30 15:38 | 8m | — | 1.4M / 38k | $0.040 | deterministic 1, grader_error 0, n_actions 2110, video_rendered 1 |
| L✗ 1h 00m | 09-30 05:42 | 1h 00m | — | 3.9M / 42k | $0.069 | deterministic 1, grader_error 0, live_success 0, video_rendered 1 |
Task instruction (upstream)
Pick up the socket with one arm and the peg with the other, lift both, and insert the peg into the socket.
Recorded by us: our scripted IK oracle (it reads object and target poses from the simulator) replayed from the task's frozen start in plain MuJoCo. Playground ships no demonstrations; its reference solutions are trained RL policies.
What MuJoCo Playground (manipulation) states about this task
| Defined in | mujoco_playground/_src/manipulation/aloha/single_peg_insertion.py |
| Env | AlohaSinglePegInsertion |
| Robot | ALOHA 2 (two ViperX 300s arms) |
| Control Hz | 400 |
| Episode S | 2.5 |
| Metric | Playground: dense RL reward, no success test |
From https://github.com/google-deepmind/mujoco_playground @ 4057c14.
Measured on the stack we run — MuJoCo 3.3.7 (CPU, bit-exact replay), Playground's scene XML @ 4057c14 + MuJoCo Menagerie 1b86ece, 50 Hz control
| Harness Task | mujoco_playground_aloha_single_peg_insertion |
| Success Test | ours: peg tip within 5 mm of the socket's axis and at least 25 % of the socket's depth inside it, at the end of the trajectory |
| Oracle | scripted IK oracle (privileged state), replayed in the verifier: success 1, deterministic 1 |
Read from run in plain MuJoCo (robot_coding_bench tasks/mujoco_playground_aloha_single_peg_insertion, image rcb-mujoco 0.1.1), 2026-09-28.
Tags¶
Why this task is interesting¶
Not yet written.
Capability notes¶
Not yet written.
Oracle demo review¶
Not yet reviewed.