Nao233's picture
First Push
621768b verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8888140916824341,
"min": 0.8888140916824341,
"max": 2.863177537918091,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8447.2890625,
"min": 8447.2890625,
"max": 29227.31640625,
"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": 12.758942604064941,
"min": 0.3752240836620331,
"max": 12.828256607055664,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2487.993896484375,
"min": 72.79347229003906,
"max": 2621.3232421875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07102612467978735,
"min": 0.060064911014848676,
"max": 0.07236097875854695,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2841044987191494,
"min": 0.2402596440593947,
"max": 0.3618048937927348,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.23471790259959652,
"min": 0.11266386901329764,
"max": 0.28273281520780397,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9388716103983861,
"min": 0.45065547605319056,
"max": 1.3346999495052823,
"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.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.Environment.CumulativeReward.mean": {
"value": 24.65909090909091,
"min": 3.1818181818181817,
"max": 25.59090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1085.0,
"min": 140.0,
"max": 1365.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.65909090909091,
"min": 3.1818181818181817,
"max": 25.59090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1085.0,
"min": 140.0,
"max": 1365.0,
"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": "1761203568",
"python_version": "3.10.12 (main, Aug 15 2025, 14:32:43) [GCC 11.4.0]",
"command_line_arguments": "/content/myenv/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1761203997"
},
"total": 428.934346816,
"count": 1,
"self": 0.743381017000047,
"children": {
"run_training.setup": {
"total": 0.022525576999896657,
"count": 1,
"self": 0.022525576999896657
},
"TrainerController.start_learning": {
"total": 428.1684402220001,
"count": 1,
"self": 0.3537234070015529,
"children": {
"TrainerController._reset_env": {
"total": 3.4994917789999818,
"count": 1,
"self": 3.4994917789999818
},
"TrainerController.advance": {
"total": 424.19233184499853,
"count": 18192,
"self": 0.3594970569852194,
"children": {
"env_step": {
"total": 305.8084165490036,
"count": 18192,
"self": 239.21603010601893,
"children": {
"SubprocessEnvManager._take_step": {
"total": 66.37751131199411,
"count": 18192,
"self": 1.2392442169855258,
"children": {
"TorchPolicy.evaluate": {
"total": 65.13826709500859,
"count": 18192,
"self": 65.13826709500859
}
}
},
"workers": {
"total": 0.21487513099054922,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 426.36678573500376,
"count": 18192,
"is_parallel": true,
"self": 216.51046948399016,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005850068999961877,
"count": 1,
"is_parallel": true,
"self": 0.004070042999728685,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017800260002331925,
"count": 10,
"is_parallel": true,
"self": 0.0017800260002331925
}
}
},
"UnityEnvironment.step": {
"total": 0.03349697099997684,
"count": 1,
"is_parallel": true,
"self": 0.0006065909997232666,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003938950001156627,
"count": 1,
"is_parallel": true,
"self": 0.0003938950001156627
},
"communicator.exchange": {
"total": 0.03060721600013494,
"count": 1,
"is_parallel": true,
"self": 0.03060721600013494
},
"steps_from_proto": {
"total": 0.0018892690000029688,
"count": 1,
"is_parallel": true,
"self": 0.0003658910004560312,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015233779995469376,
"count": 10,
"is_parallel": true,
"self": 0.0015233779995469376
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 209.8563162510136,
"count": 18191,
"is_parallel": true,
"self": 9.944946254014667,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.273747646998345,
"count": 18191,
"is_parallel": true,
"self": 5.273747646998345
},
"communicator.exchange": {
"total": 159.40170167200836,
"count": 18191,
"is_parallel": true,
"self": 159.40170167200836
},
"steps_from_proto": {
"total": 35.235920677992226,
"count": 18191,
"is_parallel": true,
"self": 6.516877322991377,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.71904335500085,
"count": 181910,
"is_parallel": true,
"self": 28.71904335500085
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 118.02441823900972,
"count": 18192,
"self": 0.4405076750203989,
"children": {
"process_trajectory": {
"total": 25.89259660398966,
"count": 18192,
"self": 25.418109515989954,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4744870879997052,
"count": 4,
"self": 0.4744870879997052
}
}
},
"_update_policy": {
"total": 91.69131395999966,
"count": 90,
"self": 37.715188929989154,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.97612503001051,
"count": 4587,
"self": 53.97612503001051
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.24100006360095e-06,
"count": 1,
"self": 1.24100006360095e-06
},
"TrainerController._save_models": {
"total": 0.12289194999993924,
"count": 1,
"self": 0.0012361110000256303,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12165583899991361,
"count": 1,
"self": 0.12165583899991361
}
}
}
}
}
}
}