Add OGBench checkpoints (planners + invdyn for scene-play and cube-single)

checkpoints/ogbench/README.md

@@ -0,0 +1,59 @@
+# OGBench Checkpoints
+
+## Scene-Play-v0 (Manipulation)
+
+Best result: **48% GSC+Resampling+Pruning** (50 episodes, seed=0)
+
+### Checkpoints
+
+| Component | File | Training Steps | Notes |
+|-----------|------|---------------|-------|
+| Planner (original) | `scene-play/planner/state_1495000.pt` | 1.5M | `energy_based_compdfu`, batch=170, 8 GPUs |
+| Planner (ogb_v1) | `scene-play/planner/ogb_v1_state_1495000.pt` | 1.5M | Re-trained, batch=128, 4 GPUs. **Better: 52% with same invdyn** |
+| InvDyn | `scene-play/invdyn/state_1600000.pt` | 1.6M | `invdyn_scene_h150`, batch=32, horizon=150, uniform goal sampling |
+
+### Eval Configs (50 episodes, seed=0)
+
+| Config | Overall | T1 (open) | T2 (unlock) | T3 (rearrange) | T4 (drawer) | T5 (hard) |
+|--------|---------|-----------|-------------|----------------|-------------|-----------|
+| GSC | 36% | 70% | 40% | 50% | 10% | 10% |
+| GSC+Resampling (U=10,min=10) | 40% | 70% | 20% | 60% | 50% | 0% |
+| **GSC+Resamp+Pruning** | **48%** | **80%** | **50%** | **70%** | 30% | 10% |
+
+### Reproduction Commands
+
+```bash
+# GSC (baseline)
+CUDA_VISIBLE_DEVICES=0,1,2,3 torchrun --nproc_per_node=4 --master_port=29590 \
+    -m src.compdiffuser.eval_sceneplay --env scene-play-v0 \
+    --planner_name energy_based_compdfu --planner_epoch 1495000 \
+    --invdyn_name invdyn_scene_h150 --invdyn_epoch 1600000 \
+    --n_trials_per_task 10 --seed 0 \
+    --ev_cp_infer_t_type gsc --ddim_steps 50 --cond_w 2.0 \
+    --b_size_per_prob 40 --n_max_steps 1500
+
+# GSC + Resampling (uniform U=10)
+# Add: --ev_cp_infer_t_type gsc_resampling --num_resampling_steps 10 --min_resampling_steps 10
+
+# GSC + Resampling + Pruning (best)
+# Add: --ev_cp_infer_t_type gsc_resampling_pruning --num_resampling_steps 10 --min_resampling_steps 10 \
+#      --pruning_start 0.5 --cv_threshold 0.01 --undo_eta 0.5 --use_gradient_ovlp --pruning_score_type inversion
+```
+
+### Critical Training Notes
+
+- **InvDyn batch_size=32 is essential.** Batch=1024 gives 0-8%. The original invdyn_scene_h150 used batch=32.
+- **InvDyn horizon=150** enables multi-step pick-place. Horizon=12 (default) gives 0%.
+- **goal_sel_idxs must match plan_obs_select_dim**: `12 13 14 19 20 21 26 27 28 29 32 33 36 38`
+- Planner ogb_v1 (re-trained) gets 52% with same invdyn — better than original 46%.
+
+## Cube-Single-Play-v0
+
+Best result: **28% GSC+Resampling** (50 episodes, planner at 1.5M)
+
+| Component | File | Training Steps |
+|-----------|------|---------------|
+| Planner | `cube-single/planner/state_1495000.pt` | 1.5M |
+| InvDyn | `cube-single/invdyn/state_1800000.pt` | 1.8M |
+
+Cube-single invdyn was trained with batch=1024 (needs retraining with batch=32 for better results).

checkpoints/ogbench/cube-single/invdyn/state_1800000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:228dec17d03ccc9ba082cd8c32f1c038b4572b5fa804a091614b6e21513f3840
+size 33956509

checkpoints/ogbench/cube-single/planner/state_1495000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7f95b1cd27ff969898ed4e949b6985ed21ac604fb19c5a984b3a087fa06b188
+size 2863994181

checkpoints/ogbench/scene-play/invdyn/state_1600000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b864b52b3a7bd26c83080ab34815463fa3d2a1da61b57a3906c1297bfe245b39
+size 34103492

checkpoints/ogbench/scene-play/planner/ogb_v1_state_1495000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddc36ebf0fb09c96b84073b977f06060c9941d3a878c43e63745c2a7fd53164b
+size 2899018053

checkpoints/ogbench/scene-play/planner/state_1495000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:402fd3ced0010af2a835cd8d3e2db706193f886afbaf52b6b70fbb3e3650a947
+size 2899027294