From eff135a86007837669d907347c90804678075659 Mon Sep 17 00:00:00 2001 From: Dominik Moritz Roth Date: Wed, 8 Oct 2025 21:07:06 +0200 Subject: [PATCH] Update experiment_plan.md --- experiment_plan.md | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/experiment_plan.md b/experiment_plan.md index b346de4..b2fdf7f 100644 --- a/experiment_plan.md +++ b/experiment_plan.md @@ -1,7 +1,7 @@ # FastTD3 HoReKa Experiment Plan *Added by Dominik - Paper Replication Study* -## ✅ Proof of Concept Results +## Proof of Concept Results **Initial Success**: [HoReKa Dev Run](https://wandb.ai/rl-network-scaling/FastTD3_HoReKa_Dev?nw=nwuserdominik_roth) - **Task**: T1JoystickFlatTerrain @@ -10,7 +10,7 @@ - **Key Achievement**: Fixed JAX/PyTorch dtype mismatch issue (removed JAX_ENABLE_X64) - **Status**: ✅ Environment working, ready for full-scale experiments -## 🚧 Currently Running Jobs +## Currently Running Jobs ### Phase 1: MuJoCo Playground - RESUBMITTED TO H100 ✅ **NEW SLURM Job IDs**: 3371681-3371692 (12 jobs total) - Using accelerated-h100 partition (94GB GPU RAM) @@ -22,7 +22,7 @@ - **Monitor**: `python monitor_experiments.py experiment_tracking_1753312228.yaml --watch` - **Note**: Previous jobs (3367710-3367723) crashed due to insufficient GPU RAM on standard partition -## 📋 TODO List +## TODO List ### Phase 1: MuJoCo Playground - [x] Set up MuJoCo Playground environment @@ -52,7 +52,7 @@ - [ ] Document findings and performance - [ ] Create final report -## 📊 Experiment Details +## Experiment Details ### Phase 1: MuJoCo Playground (Figure 11 from paper) - `T1JoystickFlatTerrain`, `T1JoystickRoughTerrain`, `G1JoystickFlatTerrain`, `G1JoystickRoughTerrain`