CAMP RMBench policies (inference weights only)

README.md

@@ -0,0 +1,64 @@
+---
+license: mit
+tags:
+- robotics
+- imitation-learning
+- diffusion-policy
+- memory
+- rmbench
+- robotwin
+---
+
+# CAMP on RMBench
+
+Policies for the paper **"Remember what you did: learning behavioral memory for robot manipulation"**
+([CAMP](https://robo-camp.github.io/), code: https://github.com/ucsdarclab/CAMP), trained on the
+[RMBench](https://github.com/robotwin-Platform/rmbench) (RoboTwin 2.0, Aloha-AgileX) benchmark from the 50 released
+demonstrations per task. Evaluated with RMBench's own protocol (`demo_clean`, seeds from 100000 validated by the
+scripted expert, per-task step limits, 100 episodes).
+
+| task | success (100 episodes) | folder |
+|---|---|---|
+| rearrange_blocks | 100 / 100 | `rearrange_blocks/` |
+| blocks_ranking_try | 100 / 100 | `blocks_ranking_try/` |
+| put_back_block | 100 / 100 | `put_back_block/` |
+| battery_try | 97 / 100 | `battery_try/` |
+
+## Files
+
+Each task folder holds only inference weights (no optimizer, scheduler or training bookkeeping):
+
+- `policy.ckpt` — CAMP policy (Diffusion Policy conditioned on the compressed action memory), EMA weights and the
+  resolved training config.
+- `memory/best_model.pt` — the Stage-1 action-memory LSTM (weights + architecture args) the policy was trained with.
+- `memory/normalizer.pt` — its input normaliser.
+
+## Recipe (all tasks)
+
+- Stage 1: memory LSTM pretrained on the 50 demos to reconstruct its past actions (DCT heads), head camera
+  96x128 + 14-D joint state, hidden 128, action subsampling 4.
+- Stage 2: Diffusion Policy (head camera 240x320, 14-D joint targets, `n_obs_steps=1`, 8-step action chunks) conditioned on the
+  memory through a 32-D projection; memory frozen for 400 epochs, then jointly finetuned (200 epochs; put_back_block 600).
+  The checkpoint reported per task is the best one over evaluated epochs.
+
+## Usage
+
+```bash
+# inside the CAMP + RoboTwin evaluation image (see scripts/rmbench/eval in the CAMP repo)
+python scripts/rmbench/eval/rmbench_eval.py eval --task rearrange_blocks --ckpt policy --episodes 100 \
+    --ckpt_root <this repo>/stage2 --stage1_root <this repo>/stage1
+```
+where `stage2/<task>/checkpoints/policy.ckpt` and `stage1/<task>/{best_model.pt,normalizer.pt}` point at the files
+of this repo (symlink or copy). The policy adapter is `scripts/rmbench/eval/policy_CAMP` and follows RMBench's
+`get_model / eval / reset_model` interface.
+
+## Citation
+
+```bibtex
+@article{wang2026rememberdidlearningbehavioral,
+  title   = {Remember What You Did: Learning Behavioral Memory for Robot Manipulation},
+  author  = {Wang, Kuancheng and Yeom, Hyunsoo and Cao, Yifan and Zhi, Huanyu and Shinde, Ishan and Yip, Michael C.},
+  journal = {arXiv preprint arXiv:2606.21188},
+  year    = {2026}
+}
+```

battery_try/memory/best_model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db86f9fc2b07b2eddfbd796cf72a0c9994b7dba69a84988ddbc5cbd4b35d3862
+size 48728373

battery_try/memory/normalizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4abe1b4094c50e858a84ed4ca784d8d8d10e565ad14e64a383c90cd5c69b6831
+size 8309

battery_try/policy.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a40d19b37bfbace58b4d784a23b6fe3ccbf9871cc89d2e8eb29e120daa37a807
+size 1097423783

blocks_ranking_try/memory/best_model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7303dc7bbaab700f9a4b9c05978ab32b03592a6f7137650cc0a26eea9e655f6a
+size 48780853

blocks_ranking_try/memory/normalizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea4fc34749c85de310882f585e68483afe43078e62accb5b2d216408dae80684
+size 8309

blocks_ranking_try/policy.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15c08f7776126459a5a70cdb157a38246af6e56ad6c113fb8496d0a9d34e0b06
+size 1097476327

put_back_block/memory/best_model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2192a1ae0ac0bbc9391f3cacfe2599bc703cba4718227da32d8c6639d19d1a0f
+size 48712373

put_back_block/memory/normalizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22ded27b555e2d002b59f546beb1c585257e711156d052af1c8aa96c1b4d3105
+size 8309

put_back_block/policy.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36f2040334fbd872abd6ca064186ab36f145445946b97a6f28346fa11bb98748
+size 1097407847

rearrange_blocks/memory/best_model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6514124ba176f86a6e222d585963531b472675d3b1e92ce323dd72b26dfc0c1
+size 48714293

rearrange_blocks/memory/normalizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:151e5a05b9c625cdbbffa146f2fb9a5a60f5cb3cd522cbc29f53a39635650a16
+size 8309

rearrange_blocks/policy.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:555f0d878b0a0af5d0afad3ea9fc0dd180a702ede106821f6ee767daba5584fd
+size 1097409767