Raptorsj22's picture
First Push
98e695b verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7764760255813599,
"min": 0.7618395090103149,
"max": 2.8632559776306152,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7379.6279296875,
"min": 7379.6279296875,
"max": 29228.1171875,
"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": 12.915307998657227,
"min": 0.41486257314682007,
"max": 12.996642112731934,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2518.485107421875,
"min": 80.48333740234375,
"max": 2663.93701171875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07222080822872408,
"min": 0.061117778452028815,
"max": 0.07584825501704187,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2888832329148963,
"min": 0.24922669397132913,
"max": 0.3792412750852094,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.22572133463679575,
"min": 0.1258747417653235,
"max": 0.29432585945024214,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.902885338547183,
"min": 0.503498967061294,
"max": 1.444826156777494,
"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": 25.65909090909091,
"min": 3.5454545454545454,
"max": 25.89090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1129.0,
"min": 156.0,
"max": 1424.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.65909090909091,
"min": 3.5454545454545454,
"max": 25.89090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1129.0,
"min": 156.0,
"max": 1424.0,
"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": "1761485964",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.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": "1761486394"
},
"total": 430.398661952,
"count": 1,
"self": 0.4353860599998143,
"children": {
"run_training.setup": {
"total": 0.02534261800008153,
"count": 1,
"self": 0.02534261800008153
},
"TrainerController.start_learning": {
"total": 429.9379332740001,
"count": 1,
"self": 0.3380477840241838,
"children": {
"TrainerController._reset_env": {
"total": 2.7208091180000338,
"count": 1,
"self": 2.7208091180000338
},
"TrainerController.advance": {
"total": 426.7906550549759,
"count": 18192,
"self": 0.37095406994671976,
"children": {
"env_step": {
"total": 310.12962727402237,
"count": 18192,
"self": 242.74644216004288,
"children": {
"SubprocessEnvManager._take_step": {
"total": 67.17746691497098,
"count": 18192,
"self": 1.2542230449633962,
"children": {
"TorchPolicy.evaluate": {
"total": 65.92324387000758,
"count": 18192,
"self": 65.92324387000758
}
}
},
"workers": {
"total": 0.2057181990085155,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 428.27198108697905,
"count": 18192,
"is_parallel": true,
"self": 214.81560422900282,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00517285700004777,
"count": 1,
"is_parallel": true,
"self": 0.00353756400011207,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016352929999357002,
"count": 10,
"is_parallel": true,
"self": 0.0016352929999357002
}
}
},
"UnityEnvironment.step": {
"total": 0.03463284300005398,
"count": 1,
"is_parallel": true,
"self": 0.0005758720001267648,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004246729999977106,
"count": 1,
"is_parallel": true,
"self": 0.0004246729999977106
},
"communicator.exchange": {
"total": 0.03181576099996164,
"count": 1,
"is_parallel": true,
"self": 0.03181576099996164
},
"steps_from_proto": {
"total": 0.001816536999967866,
"count": 1,
"is_parallel": true,
"self": 0.0003447429996867868,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014717940002810792,
"count": 10,
"is_parallel": true,
"self": 0.0014717940002810792
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 213.45637685797624,
"count": 18191,
"is_parallel": true,
"self": 10.221908367935384,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.445265639006152,
"count": 18191,
"is_parallel": true,
"self": 5.445265639006152
},
"communicator.exchange": {
"total": 162.00637381901424,
"count": 18191,
"is_parallel": true,
"self": 162.00637381901424
},
"steps_from_proto": {
"total": 35.78282903202046,
"count": 18191,
"is_parallel": true,
"self": 6.381930603012734,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.400898429007725,
"count": 181910,
"is_parallel": true,
"self": 29.400898429007725
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 116.29007371100681,
"count": 18192,
"self": 0.4094349260182071,
"children": {
"process_trajectory": {
"total": 25.858066458988333,
"count": 18192,
"self": 25.34866324498853,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5094032139998035,
"count": 4,
"self": 0.5094032139998035
}
}
},
"_update_policy": {
"total": 90.02257232600027,
"count": 90,
"self": 36.76565391399879,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.25691841200148,
"count": 4587,
"self": 53.25691841200148
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2149998838140164e-06,
"count": 1,
"self": 1.2149998838140164e-06
},
"TrainerController._save_models": {
"total": 0.08842010200010009,
"count": 1,
"self": 0.0008102830001917027,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08760981899990838,
"count": 1,
"self": 0.08760981899990838
}
}
}
}
}
}
}