Add model card, weights, video, TB

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+replay.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,91 @@
+---
+license: mit
+library_name: marl-ppo-suite
+tags:
+- reinforcement-learning
+- starcraft-mac
+- smacv2
+- mappo
+- terran_10_vs_10
+- smacv2_terran_10_vs_10
+model-index:
+- name: MAPPO on smacv2_terran_10_vs_10
+  results:
+  - task:
+      type: reinforcement-learning
+      name: StarCraft Multi-Agent Challenge v2
+    dataset:
+      name: terran_10_vs_10
+      type: smacv2
+    metrics:
+      - name: win-rate
+        type: win_rate
+        value: 0.566
+      - name: mean-reward
+        type: mean_reward
+        value: 16.68
+      - name: mean-ep-length
+        type: mean_episode_length
+        value: 51.4
+---
+
+# MAPPO on **smacv2_terran_10_vs_10**
+
+*10 M environment steps · 14.47 h wall-clock · seed 1*
+
+This is a trained model of a `MAPPO` agent playing *smacv2_terran_10_vs_10*.  
+The model was produced with the open-source
+[`marl-ppo-suite`](https://github.com/legalaspro/marl-ppo-suite) training
+code.
+
+
+
+## Usage  – quick evaluation / replay
+
+```bash
+# 1. install the codebase (directly from GitHub)
+pip install "marl-ppo-suite @ git+https://github.com/legalaspro/marl-ppo-suite"
+
+# 2. get the weights & config from HF
+wget https://huggingface.co/<repo-id>/resolve/main/final-torch.model
+wget https://huggingface.co/<repo-id>/resolve/main/config.json
+
+# 3-a. Generate a StarCraft II replay file 1 episode in starcraft replay folder
+marl-train   --mode render   --model final-torch.model   --config config.json   --render_episodes 1 \       
+
+# 3-b. generate additionally video drawn from frames 
+marl-train   --mode render   --model final-torch.model   --config config.json   --render_episodes 1   --render_mode rgb_array       
+```
+
+## Files
+
+* **`final-torch.model`** – PyTorch checkpoint  
+* **`replay.mp4`** – gameplay of the final policy 
+* **`config.json`** – training config
+* **`tensorboard/`** – full logs
+
+## Hyper-parameters
+
+```python
+{
+  "clip_param": 0.05,
+  "data_chunk_length": 10,
+  "entropy_coef": 0.01,
+  "fc_layers": 2,
+  "gae_lambda": 0.95,
+  "gamma": 0.99,
+  "hidden_size": 64,
+  "lr": 0.0005,
+  "n_steps": 200,
+  "num_mini_batch": 1,
+  "ppo_epoch": 5,
+  "reward_norm_type": "efficient",
+  "seed": 1,
+  "state_type": "AS",
+  "use_reward_norm": true,
+  "use_rnn": true,
+  "use_value_norm": false,
+  "value_norm_type": "welford"
+}
+```
+

config.json

@@ -0,0 +1,59 @@
+{
+  "lr": 0.0005,
+  "algo": "mappo",
+  "cuda": true,
+  "mode": "train",
+  "seed": 1,
+  "boost": false,
+  "gamma": 0.99,
+  "model": null,
+  "config": null,
+  "min_lr": 1e-05,
+  "n_steps": 200,
+  "use_gae": true,
+  "use_rnn": true,
+  "env_name": "smacv2",
+  "map_name": "terran_10_vs_10",
+  "n_agents": 10,
+  "use_eval": true,
+  "fc_layers": 2,
+  "max_steps": 10000000,
+  "ppo_epoch": 5,
+  "use_wandb": true,
+  "actor_gain": 0.01,
+  "clip_param": 0.05,
+  "gae_lambda": 0.95,
+  "rnn_layers": 1,
+  "state_type": "AS",
+  "fixed_order": false,
+  "hidden_size": 64,
+  "huber_delta": 10,
+  "render_mode": "human",
+  "entropy_coef": 0.01,
+  "log_interval": 16000,
+  "use_agent_id": false,
+  "capture_video": true,
+  "eval_episodes": 32,
+  "eval_interval": 80000,
+  "max_grad_norm": 10,
+  "optimizer_eps": 1e-05,
+  "torch_threads": null,
+  "num_mini_batch": 1,
+  "use_huber_loss": false,
+  "use_value_norm": false,
+  "render_episodes": 10,
+  "use_reward_norm": true,
+  "value_norm_type": "welford",
+  "reward_norm_type": "efficient",
+  "data_chunk_length": 10,
+  "n_rollout_threads": 16,
+  "use_death_masking": false,
+  "use_max_grad_norm": true,
+  "cuda_deterministic": true,
+  "use_linear_lr_decay": false,
+  "capture_video_interval": 200000,
+  "n_eval_rollout_threads": 4,
+  "use_clipped_value_loss": true,
+  "use_proper_time_limits": true,
+  "use_feature_normalization": true
+}

final-torch.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81939272bf77a71367c4573056f571867ac06df18b030c3b294b1eaea7a6dfa0
+size 1250679

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49666165751301936139f345b587ed3320e192869838192838301cfd73943a99
+size 379203

tensorboard/events.out.tfevents.1747157979.ubuntu-32gb-marl.3444287.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c80630994fa46f81aec2e20da8f8940da515be8dadda6b5b289bce3d26ff2a5
+size 409315