dppo/EXPERIMENT_PLAN.md
ys1087@partner.kit.edu cb9846484f Update experiment plan with validation results and WandB URLs
- Complete validation status table with results for all environments
- Add WandB tracking URLs for completed fine-tuning runs
- Document technical fixes and current job queue status
- Add test scripts for remaining D3IL avoid_m3 and robomimic transport validation
2025-08-27 22:14:10 +02:00

1.7 KiB

DPPO Validation Status

Environment Testing Progress

Environment Pre-train Fine-tune Result WandB URL
Gym (MuJoCo)
hopper-medium-v2 Complete Complete 1415.85 Run
walker2d-medium-v2 Complete Complete 2977.97 Run
halfcheetah-medium-v2 Complete Complete 4058.34 Run
Robomimic
lift Complete Complete 69% success Run
can Complete Complete 85.89% success Run
square Complete Running (job 3446120) Pending -
transport Complete Running (job 3446147) Pending -
D3IL
avoid_m1 Complete Complete 87.7 reward Run
avoid_m2 Complete Complete 82.46 reward Run
avoid_m3 Ready Queued (job 3446146) Pending -

Technical Issues Resolved

  • MuJoCo compilation with Intel compiler (GCC wrapper solution)
  • SLURM job scheduling and resource allocation
  • WandB logging configuration
  • Configuration parameter corrections for D3IL

Next Steps

  1. Complete remaining validation runs
  2. Begin full paper replication experiments
  3. Generate performance comparison tables