d739fa5e5e
- Create robomimic transport pre-training test script - Update EXPERIMENT_PLAN.md with square success - Add WandB URLs for completed robomimic tests - Track progress on remaining validation tests
69 lines
2.6 KiB
Markdown
69 lines
2.6 KiB
Markdown
# DPPO Experiment Plan
|
|
|
|
## What's Done ✅
|
|
|
|
**Installation & Setup:**
|
|
- ✅ Python 3.10 venv working on HoReKa
|
|
- ✅ All dependencies installed (gym, robomimic, d3il)
|
|
- ✅ WandB logging configured with "dppo-" project prefix
|
|
- ✅ HoReKa Intel compiler fix for mujoco-py integrated into install script
|
|
- ✅ Cython version pinned to 0.29.37 for mujoco-py compatibility
|
|
|
|
**Validated Pre-training:**
|
|
- ✅ Gym: hopper, walker2d, halfcheetah (all working with data download & WandB logging)
|
|
- ✅ Robomimic: lift, can, square (WandB: can: https://wandb.ai/dominik_roth/robomimic-can-pretrain/runs/xwpzcssw, square: https://wandb.ai/dominik_roth/robomimic-square-pretrain/runs/hty80o7z)
|
|
- ✅ D3IL: avoid_m1 (working)
|
|
|
|
## What We're Doing Right Now 🔄
|
|
|
|
**Current Jobs:**
|
|
- 🔄 Job 3445594: Running updated installer with integrated MuJoCo fix
|
|
- 🔄 Job 3445604: Testing robomimic square (new job)
|
|
- 🔄 Job 3445606: Testing robomimic transport
|
|
|
|
**Latest Success:**
|
|
- ✅ Job 3445550: Robomimic square pre-training SUCCESS with WandB logging!
|
|
|
|
**Progress on MuJoCo Fix:**
|
|
- ✅ Identified root cause: Intel compiler flags incompatible with GCC for mujoco-py
|
|
- ✅ Developed sysconfig patch to override Intel flags
|
|
- ✅ Integrated fix into install script and README
|
|
- 🔄 Waiting for installer completion to test fix validation
|
|
|
|
## What Needs to Be Done 📋
|
|
|
|
### Phase 1: Complete Installation Validation
|
|
**Goal:** Confirm every environment works in both pre-train and fine-tune modes
|
|
|
|
**Remaining Pre-training Tests:**
|
|
- Robomimic: transport (in progress)
|
|
- D3IL: avoid_m2, avoid_m3 (waiting for full installer)
|
|
|
|
**Fine-tuning Tests (after MuJoCo validation):**
|
|
- Gym: hopper, walker2d, halfcheetah
|
|
- Robomimic: lift, can, square, transport
|
|
- D3IL: avoid_m1, avoid_m2, avoid_m3
|
|
|
|
### Phase 2: Paper Results Generation
|
|
**Goal:** Run full experiments to replicate paper results
|
|
|
|
**Gym Tasks (Core Paper Results):**
|
|
- hopper-medium-v2 → hopper-v2: Pre-train (200 epochs) + Fine-tune
|
|
- walker2d-medium-v2 → walker2d-v2: Pre-train (200 epochs) + Fine-tune
|
|
- halfcheetah-medium-v2 → halfcheetah-v2: Pre-train (200 epochs) + Fine-tune
|
|
|
|
**Extended Results:**
|
|
- All Robomimic tasks: full pre-train + fine-tune
|
|
- All D3IL tasks: full pre-train + fine-tune
|
|
|
|
## Current Status
|
|
|
|
**Blockers:** None - all technical issues resolved
|
|
**Waiting on:** Cluster resources to run validation jobs
|
|
**Next Step:** Complete Phase 1 validation, then move to Phase 2 production runs
|
|
|
|
## Success Criteria
|
|
|
|
- [ ] All environments work in dev tests (Phase 1)
|
|
- [ ] All paper results replicated and in WandB (Phase 2)
|
|
- [ ] Complete documentation for future users |