{
  "model_type": "marl-ippo-actor-critic",
  "name": "MARL IPPO Warehouse Cube Sorting Policy",
  "description": "Independent PPO policies for 2-4 mobile warehouse robots in NVIDIA Isaac Sim, with optional world-model imagination.",
  "task": "multi-agent-warehouse-cube-sorting",
  "simulator": {
    "name": "NVIDIA Isaac Sim",
    "versions_tested": ["5.1.0", "6.0.1 pip"],
    "headless": true,
    "renderer": "D3D12"
  },
  "num_agents": 2,
  "observation": {
    "image": {
      "shape": [3, 128, 128],
      "dtype": "uint8",
      "description": "RGB camera image per agent, stored/transposed to CHW for the policy network."
    },
    "state": {
      "shape": [12],
      "dtype": "float32",
      "description": "[x, y, yaw, vx, vy, omega, nearest_cube_dx, nearest_cube_dy, nearest_cube_dist, target_bin_dx, target_bin_dy, target_bin_dist]"
    }
  },
  "action_space": {
    "type": "continuous",
    "shape": [4],
    "low": -1.0,
    "high": 1.0,
    "description": "[forward, lateral, angular, gripper]",
    "gripper_threshold": 0.5
  },
  "policy": {
    "algorithm": "IPPO",
    "architecture": {
      "image_encoder": {
        "type": "CNN",
        "input_shape": [3, 128, 128],
        "conv_layers": [
          {"in_channels": 3, "out_channels": 32, "kernel_size": 3, "stride": 2, "padding": 1},
          {"in_channels": 32, "out_channels": 64, "kernel_size": 3, "stride": 2, "padding": 1},
          {"in_channels": 64, "out_channels": 64, "kernel_size": 3, "stride": 2, "padding": 1}
        ],
        "pooling": "AdaptiveAvgPool2d(4, 4)"
      },
      "shared_mlp": {
        "input_dim": "conv_flat + state_dim",
        "hidden_dim": 256,
        "num_layers": 2,
        "activation": "ReLU"
      },
      "value_head": {"input_dim": 256, "output_dim": 1},
      "actor_head": {
        "type": "gaussian",
        "input_dim": 256,
        "output_dim": 4
      },
      "state_dim": 12,
      "hidden_dim": 256,
      "cnn_channels": [32, 64, 64],
      "reduce_spatial": 4
    },
    "hyperparameters": {
      "lr": 3e-4,
      "gamma": 0.99,
      "gae_lambda": 0.95,
      "clip_eps": 0.2,
      "value_loss_coef": 0.5,
      "entropy_coef": 0.01,
      "update_epochs": 4,
      "batch_size": 64,
      "max_grad_norm": 0.5,
      "normalize_advantages": true
    }
  },
  "world_model": {
    "backends": ["mock", "cosmos3", "dreamdojo"],
    "default": "mock",
    "fallback_to_mock": true,
    "imagination_horizon_default": 20
  },
  "so101_bridge": {
    "input_image_size": [128, 128],
    "state_dim_policy": 12,
    "action_mode": "delta",
    "max_delta": 0.05,
    "joint_keys": [
      "shoulder_pan.pos",
      "shoulder_lift.pos",
      "elbow_flex.pos",
      "wrist_flex.pos",
      "wrist_roll.pos",
      "gripper.pos"
    ]
  },
  "lerobot_dataset_repo": "Ryukijano/marl-world-model-lerobot",
  "source_repo": "Ryukijano/marl-world-model",
  "license": "apache-2.0"
}