environment_metadata.json

{
  "observation_space": {
    "type": "Box",
    "shape": [
      24
    ],
    "components": {
      "program_features": {
        "indices": [
          0,
          7
        ],
        "dim": 8
      },
      "flag_state": {
        "indices": [
          8,
          19
        ],
        "dim": 12
      },
      "base_onehot": {
        "indices": [
          20,
          23
        ],
        "dim": 4
      }
    }
  },
  "action_space": {
    "type": "Discrete",
    "n": 17,
    "mapping": {
      "0": "STOP",
      "1": "toggle_march-native",
      "2": "toggle_ftree-vectorize",
      "3": "toggle_ffast-math",
      "4": "toggle_funroll-loops",
      "5": "toggle_fpeel-loops",
      "6": "toggle_ftree-loop-distribution",
      "7": "toggle_finline-functions",
      "8": "toggle_flto",
      "9": "toggle_fschedule-insns2",
      "10": "toggle_fomit-frame-pointer",
      "11": "toggle_fstrict-aliasing",
      "12": "toggle_ftree-loop-vectorize",
      "13": "set_base_O1",
      "14": "set_base_O2",
      "15": "set_base_O3",
      "16": "set_base_Ofast"
    }
  },
  "max_episode_steps": 5,
  "reward_type": "potential_based_shaping_plus_log_ratio",
  "curriculum_phases": [
    {
      "name": "beat_O0",
      "range": [
        0,
        20000
      ]
    },
    {
      "name": "beat_O1",
      "range": [
        20000,
        80000
      ]
    },
    {
      "name": "beat_O2",
      "range": [
        80000,
        500000
      ]
    },
    {
      "name": "beat_best_known",
      "range": [
        500000,
        null
      ]
    }
  ],
  "framework": "stable-baselines3",
  "algorithm": "PPO",
  "policy": "MlpPolicy"
}