Add DMM checkpoints and model card

DMM-08M.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d6017bd8d274ff62a1987ab943763952d97f2ca64f3a4b829dcb3e2853910e5
+size 3076725

DMM-3M.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20ac0bb4b88fd4904e49d15d8e88ab1d7b768c37fba43806ab9bc643c5aa5916
+size 13028093

DMM-MICPO-08M.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fcd798143fef80f2efd936875e5648c5bd505cdaee498601adfa11a44f38d3a
+size 3079541

DMM-MICPO-3M.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69fc0dd5c05ce394148646d225e8740ec385958e443ce400a58499ee8c77d38d
+size 13036441

README.md

@@ -1,3 +1,30 @@
 ---
 license: mit
+tags:
+  - pytorch
+  - multi-agent-path-finding
+  - mapf
+  - decentralized
 ---
+
+# DMM: Decentralized Master-Mind
+
+DMM is a decentralized multi-agent pathfinding policy that refines agents' action
+intents over several local communication rounds before committing to actions.
+The models are pretrained on expert solutions with imitation learning and
+optionally fine-tuned with MICPO, a critic-free reinforcement learning method.
+
+[Paper](https://arxiv.org/abs/2609.32019) · [Code](https://github.com/CognitiveAISystems/DMM)
+
+| Checkpoint | Imitation pretraining iterations | MICPO optimizer updates |
+| --- | ---: | ---: |
+| [DMM-08M.pt](DMM-08M.pt) | 1,000,000 | — |
+| [DMM-3M.pt](DMM-3M.pt) | 1,000,000 | — |
+| [DMM-MICPO-08M.pt](DMM-MICPO-08M.pt) | 1,000,000 | 96,000 |
+| [DMM-MICPO-3M.pt](DMM-MICPO-3M.pt) | 1,000,000 | 96,000 |
+
+MICPO fine-tuning comprises 500 outer iterations (96,000 optimizer updates).
+Both model sizes use four communication rounds. Training details are reported in
+[the paper](https://arxiv.org/html/2609.32019v1#S5.SS1).
+
+See the [GitHub repository](https://github.com/CognitiveAISystems/DMM) for code, usage instructions, training, and evaluation.