# 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)**: 24 tasks - **COMPLETED**
- AcrobotSwingup, CartpoleBalance, CheetahRun, FingerSpin, HumanoidRun, WalkerRun, etc.
- Results: https://wandb.ai/dominik_roth/reppo_dmc_production

**ManiSkill Suite**: 8 tasks (need wrapper first)
- PickSingleYCB-v1, PegInsertionSide-v1, UnitreeG1TransportBox-v1, etc.

**Settings**: 50M steps, 1024 envs, 3 seeds each, paper hyperparameters

## Scripts Available

### DMC Experiments
```bash
# Submit all 24 DMC tasks with 3 seeds each
python submit_dmc_experiments.py --seeds 3

# Submit specific tasks
python submit_dmc_experiments.py --tasks CartpoleBalance CheetahRun --seeds 3
```

### Brax Experiments (Already completed)
```bash  
./submit_job.sh brax ant mjx_dmc_medium_data
./submit_job.sh brax cheetah mjx_dmc_medium_data
```