30 lines
959 B
Markdown
30 lines
959 B
Markdown
# REPPO Experiment Plan
|
|
|
|
## Proof of Concept Success
|
|
✅ **Working Implementation**: https://wandb.ai/dominik_roth/reppo_dev_test?nw=nwuserdominik_roth
|
|
|
|
## Experiments To Run
|
|
|
|
### 1. Reproduce Paper Results
|
|
|
|
✅ **Brax Suite**: 5 tasks - **COMPLETED**
|
|
- ant, cheetah, humanoid, walker, hopper
|
|
- Results: https://wandb.ai/dominik_roth/reppo_brax_production
|
|
|
|
**DMC Suite (mujoco_playground)**: 23 tasks
|
|
- AcrobotSwingup, CartpoleBalance, CheetahRun, FingerSpin, HumanoidRun, WalkerRun, etc.
|
|
|
|
**ManiSkill Suite**: 8 tasks (need wrapper first)
|
|
- PickSingleYCB-v1, PegInsertionSide-v1, UnitreeG1TransportBox-v1, etc.
|
|
|
|
**Settings**: 50M steps, 1024 envs, 5 seeds each, paper hyperparameters
|
|
|
|
## Scripts Needed
|
|
|
|
### `submit_experiments.py`
|
|
Uses existing working SLURM script:
|
|
```bash
|
|
python submit_experiments.py --experiment brax --seeds 5
|
|
python submit_experiments.py --experiment mjx --seeds 5
|
|
python submit_experiments.py --experiment maniskill --seeds 5
|
|
``` |