gurpreetmukker's picture
First Push
01ebdfa
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0540051460266113,
"min": 1.0540051460266113,
"max": 2.859013080596924,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10063.6416015625,
"min": 10063.6416015625,
"max": 29467.84765625,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.862473487854004,
"min": 0.3197285234928131,
"max": 12.862473487854004,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2508.182373046875,
"min": 62.0273323059082,
"max": 2594.656005859375,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06102748657525024,
"min": 0.06039725248532098,
"max": 0.0735148064486566,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.24410994630100097,
"min": 0.24158900994128393,
"max": 0.36307734960585136,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21413043002579726,
"min": 0.10744886025421177,
"max": 0.27775755933686797,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.856521720103189,
"min": 0.4297954410168471,
"max": 1.2926808607344533,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 24.681818181818183,
"min": 3.272727272727273,
"max": 25.545454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1086.0,
"min": 144.0,
"max": 1405.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.681818181818183,
"min": 3.272727272727273,
"max": 25.545454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1086.0,
"min": 144.0,
"max": 1405.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1702067351",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1702067854"
},
"total": 502.4352765509999,
"count": 1,
"self": 0.4397214109998231,
"children": {
"run_training.setup": {
"total": 0.06021157000009225,
"count": 1,
"self": 0.06021157000009225
},
"TrainerController.start_learning": {
"total": 501.93534357,
"count": 1,
"self": 0.6453510929887898,
"children": {
"TrainerController._reset_env": {
"total": 3.5568995620000123,
"count": 1,
"self": 3.5568995620000123
},
"TrainerController.advance": {
"total": 497.6434372690112,
"count": 18199,
"self": 0.33260941303183245,
"children": {
"env_step": {
"total": 497.31082785597937,
"count": 18199,
"self": 338.3353233719905,
"children": {
"SubprocessEnvManager._take_step": {
"total": 158.64971057099967,
"count": 18199,
"self": 1.5894547760027535,
"children": {
"TorchPolicy.evaluate": {
"total": 157.06025579499692,
"count": 18199,
"self": 157.06025579499692
}
}
},
"workers": {
"total": 0.3257939129891838,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 500.4759700210137,
"count": 18199,
"is_parallel": true,
"self": 243.49861651702747,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0051639400001022295,
"count": 1,
"is_parallel": true,
"self": 0.0037136119999559014,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014503280001463281,
"count": 10,
"is_parallel": true,
"self": 0.0014503280001463281
}
}
},
"UnityEnvironment.step": {
"total": 0.03626332999999704,
"count": 1,
"is_parallel": true,
"self": 0.0006611380000549616,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00044119999995473336,
"count": 1,
"is_parallel": true,
"self": 0.00044119999995473336
},
"communicator.exchange": {
"total": 0.03303805600000942,
"count": 1,
"is_parallel": true,
"self": 0.03303805600000942
},
"steps_from_proto": {
"total": 0.0021229359999779263,
"count": 1,
"is_parallel": true,
"self": 0.00041966199978560326,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001703274000192323,
"count": 10,
"is_parallel": true,
"self": 0.001703274000192323
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 256.97735350398625,
"count": 18198,
"is_parallel": true,
"self": 11.012263498006064,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.746085055987464,
"count": 18198,
"is_parallel": true,
"self": 5.746085055987464
},
"communicator.exchange": {
"total": 203.588841507006,
"count": 18198,
"is_parallel": true,
"self": 203.588841507006
},
"steps_from_proto": {
"total": 36.630163442986714,
"count": 18198,
"is_parallel": true,
"self": 7.115723770954787,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.514439672031926,
"count": 181980,
"is_parallel": true,
"self": 29.514439672031926
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00013623899985759635,
"count": 1,
"self": 0.00013623899985759635,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 493.3093822429139,
"count": 529703,
"is_parallel": true,
"self": 11.506393455860916,
"children": {
"process_trajectory": {
"total": 282.5327805000528,
"count": 529703,
"is_parallel": true,
"self": 281.73904544605296,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7937350539998533,
"count": 4,
"is_parallel": true,
"self": 0.7937350539998533
}
}
},
"_update_policy": {
"total": 199.27020828700017,
"count": 90,
"is_parallel": true,
"self": 61.02305345799289,
"children": {
"TorchPPOOptimizer.update": {
"total": 138.2471548290073,
"count": 4584,
"is_parallel": true,
"self": 138.2471548290073
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08951940700012528,
"count": 1,
"self": 0.000911240000050384,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0886081670000749,
"count": 1,
"self": 0.0886081670000749
}
}
}
}
}
}
}