omriKramer's picture
First Push
52fc9c8
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8691138029098511,
"min": 0.8691138029098511,
"max": 2.8644587993621826,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8288.73828125,
"min": 8288.73828125,
"max": 29303.4140625,
"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": 12.892515182495117,
"min": 0.4674447476863861,
"max": 12.892515182495117,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2514.04052734375,
"min": 90.68428039550781,
"max": 2611.13525390625,
"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": 0.07053038219215951,
"min": 0.057792506624907994,
"max": 0.07156672339302068,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28212152876863805,
"min": 0.2505073990586086,
"max": 0.3578336169651034,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2185695570181398,
"min": 0.13390495179462997,
"max": 0.27426393382689535,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8742782280725592,
"min": 0.5356198071785199,
"max": 1.3713196691344767,
"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": 24.954545454545453,
"min": 3.772727272727273,
"max": 25.581818181818182,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1098.0,
"min": 166.0,
"max": 1407.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.954545454545453,
"min": 3.772727272727273,
"max": 25.581818181818182,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1098.0,
"min": 166.0,
"max": 1407.0,
"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": "1701505963",
"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": "1701506435"
},
"total": 472.2979858730001,
"count": 1,
"self": 0.43466792500004203,
"children": {
"run_training.setup": {
"total": 0.05737252100004753,
"count": 1,
"self": 0.05737252100004753
},
"TrainerController.start_learning": {
"total": 471.805945427,
"count": 1,
"self": 0.5717831270014813,
"children": {
"TrainerController._reset_env": {
"total": 4.073539140999969,
"count": 1,
"self": 4.073539140999969
},
"TrainerController.advance": {
"total": 467.0760297519985,
"count": 18198,
"self": 0.270776755002089,
"children": {
"env_step": {
"total": 466.8052529969964,
"count": 18198,
"self": 315.28849626298006,
"children": {
"SubprocessEnvManager._take_step": {
"total": 151.2249308260075,
"count": 18198,
"self": 1.4608037100120441,
"children": {
"TorchPolicy.evaluate": {
"total": 149.76412711599545,
"count": 18198,
"self": 149.76412711599545
}
}
},
"workers": {
"total": 0.2918259080088319,
"count": 18198,
"self": 0.0,
"children": {
"worker_root": {
"total": 470.5074800160078,
"count": 18198,
"is_parallel": true,
"self": 231.17432086900266,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0057149279999748615,
"count": 1,
"is_parallel": true,
"self": 0.004088709000029667,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016262189999451948,
"count": 10,
"is_parallel": true,
"self": 0.0016262189999451948
}
}
},
"UnityEnvironment.step": {
"total": 0.04956928200004995,
"count": 1,
"is_parallel": true,
"self": 0.0007051590000628494,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00026792500000283326,
"count": 1,
"is_parallel": true,
"self": 0.00026792500000283326
},
"communicator.exchange": {
"total": 0.0466719130000115,
"count": 1,
"is_parallel": true,
"self": 0.0466719130000115
},
"steps_from_proto": {
"total": 0.0019242849999727696,
"count": 1,
"is_parallel": true,
"self": 0.0003500130000588797,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015742719999138899,
"count": 10,
"is_parallel": true,
"self": 0.0015742719999138899
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 239.33315914700512,
"count": 18197,
"is_parallel": true,
"self": 10.697036191000734,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.298259622005844,
"count": 18197,
"is_parallel": true,
"self": 5.298259622005844
},
"communicator.exchange": {
"total": 190.00068329600055,
"count": 18197,
"is_parallel": true,
"self": 190.00068329600055
},
"steps_from_proto": {
"total": 33.337180037997996,
"count": 18197,
"is_parallel": true,
"self": 6.232832034012915,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.10434800398508,
"count": 181970,
"is_parallel": true,
"self": 27.10434800398508
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012274300001990923,
"count": 1,
"self": 0.00012274300001990923,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 463.0580529729632,
"count": 497242,
"is_parallel": true,
"self": 10.743500275962504,
"children": {
"process_trajectory": {
"total": 261.6027227110009,
"count": 497242,
"is_parallel": true,
"self": 260.91361817400076,
"children": {
"RLTrainer._checkpoint": {
"total": 0.689104537000162,
"count": 4,
"is_parallel": true,
"self": 0.689104537000162
}
}
},
"_update_policy": {
"total": 190.71182998599977,
"count": 90,
"is_parallel": true,
"self": 58.197133792996,
"children": {
"TorchPPOOptimizer.update": {
"total": 132.51469619300377,
"count": 4587,
"is_parallel": true,
"self": 132.51469619300377
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08447066400003678,
"count": 1,
"self": 0.0009770210000397128,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08349364299999706,
"count": 1,
"self": 0.08349364299999706
}
}
}
}
}
}
}