processor.json

{
  "name": "StatefulProcessor",
  "seed": 42,
  "steps": [
    {
      "registry_name": "adaptive_normalizer",
      "config": {
        "name": "obs_normalizer",
        "learning_rate": 0.005,
        "warmup_steps": 50,
        "outlier_threshold": 2.5,
        "epsilon": 1e-08
      },
      "state_file": "step_0.safetensors"
    },
    {
      "registry_name": "temporal_reward_shaper",
      "config": {
        "name": "reward_shaper",
        "buffer_size": 100,
        "momentum_decay": 0.95,
        "bonus_scale": 0.05,
        "improvement_threshold": 0.1
      },
      "state_file": "step_1.safetensors"
    }
  ]
}