AdityaBajracharya's picture
First Push
9e7905a verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0572841167449951,
"min": 1.0572841167449951,
"max": 2.887760639190674,
"count": 30
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10885.796875,
"min": 10115.8173828125,
"max": 29478.259765625,
"count": 30
},
"SnowballTarget.Step.mean": {
"value": 299968.0,
"min": 9952.0,
"max": 299968.0,
"count": 30
},
"SnowballTarget.Step.sum": {
"value": 299968.0,
"min": 9952.0,
"max": 299968.0,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 11.740798950195312,
"min": 0.30327433347702026,
"max": 11.740798950195312,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2395.123046875,
"min": 58.83522033691406,
"max": 2395.123046875,
"count": 30
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06644381413866274,
"min": 0.05957100111332051,
"max": 0.0774127382205288,
"count": 30
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3322190706933137,
"min": 0.23828400445328204,
"max": 0.36189745243709515,
"count": 30
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.22719829742814981,
"min": 0.09005664846649869,
"max": 0.2732214044560405,
"count": 30
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.135991487140749,
"min": 0.36022659386599476,
"max": 1.356526905999464,
"count": 30
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.762764903999999e-06,
"min": 1.762764903999999e-06,
"max": 9.819600180400002e-05,
"count": 30
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 8.813824519999995e-06,
"min": 8.813824519999995e-06,
"max": 0.00047448002552,
"count": 30
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10176266666666667,
"min": 0.10176266666666667,
"max": 0.198196,
"count": 30
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.5088133333333333,
"min": 0.42025066666666666,
"max": 0.97448,
"count": 30
},
"SnowballTarget.Policy.Beta.mean": {
"value": 9.795706666666662e-05,
"min": 9.795706666666662e-05,
"max": 0.0049099804000000006,
"count": 30
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0004897853333333331,
"min": 0.0004897853333333331,
"max": 0.023726551999999998,
"count": 30
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 30
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 30
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 23.09090909090909,
"min": 2.659090909090909,
"max": 23.272727272727273,
"count": 30
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1270.0,
"min": 117.0,
"max": 1270.0,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.09090909090909,
"min": 2.659090909090909,
"max": 23.272727272727273,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1270.0,
"min": 117.0,
"max": 1270.0,
"count": 30
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 30
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 30
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1733125961",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1733126598"
},
"total": 637.6687310130001,
"count": 1,
"self": 0.4311229910001657,
"children": {
"run_training.setup": {
"total": 0.0548766809999961,
"count": 1,
"self": 0.0548766809999961
},
"TrainerController.start_learning": {
"total": 637.1827313409999,
"count": 1,
"self": 0.5134021509902595,
"children": {
"TrainerController._reset_env": {
"total": 2.0005965809998543,
"count": 1,
"self": 2.0005965809998543
},
"TrainerController.advance": {
"total": 634.5774062330097,
"count": 27328,
"self": 0.5520907460270337,
"children": {
"env_step": {
"total": 451.0978187139783,
"count": 27328,
"self": 342.24367256197957,
"children": {
"SubprocessEnvManager._take_step": {
"total": 108.5189627550235,
"count": 27328,
"self": 1.8517140330068287,
"children": {
"TorchPolicy.evaluate": {
"total": 106.66724872201667,
"count": 27328,
"self": 106.66724872201667
}
}
},
"workers": {
"total": 0.33518339697525334,
"count": 27328,
"self": 0.0,
"children": {
"worker_root": {
"total": 635.2669524610185,
"count": 27328,
"is_parallel": true,
"self": 335.9366657439916,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002434442999856401,
"count": 1,
"is_parallel": true,
"self": 0.0007289109998964705,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017055319999599305,
"count": 10,
"is_parallel": true,
"self": 0.0017055319999599305
}
}
},
"UnityEnvironment.step": {
"total": 0.038077654000062466,
"count": 1,
"is_parallel": true,
"self": 0.0006798859997161344,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00038252700005614315,
"count": 1,
"is_parallel": true,
"self": 0.00038252700005614315
},
"communicator.exchange": {
"total": 0.03508204000013393,
"count": 1,
"is_parallel": true,
"self": 0.03508204000013393
},
"steps_from_proto": {
"total": 0.0019332010001562594,
"count": 1,
"is_parallel": true,
"self": 0.0003969300000790099,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015362710000772495,
"count": 10,
"is_parallel": true,
"self": 0.0015362710000772495
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 299.33028671702687,
"count": 27327,
"is_parallel": true,
"self": 14.912661805052949,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 8.200302507004153,
"count": 27327,
"is_parallel": true,
"self": 8.200302507004153
},
"communicator.exchange": {
"total": 227.57095005097517,
"count": 27327,
"is_parallel": true,
"self": 227.57095005097517
},
"steps_from_proto": {
"total": 48.64637235399459,
"count": 27327,
"is_parallel": true,
"self": 8.675129428966784,
"children": {
"_process_rank_one_or_two_observation": {
"total": 39.97124292502781,
"count": 273270,
"is_parallel": true,
"self": 39.97124292502781
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 182.92749677300435,
"count": 27328,
"self": 0.5955422770125551,
"children": {
"process_trajectory": {
"total": 42.84768608299305,
"count": 27328,
"self": 42.135167447993126,
"children": {
"RLTrainer._checkpoint": {
"total": 0.712518634999924,
"count": 6,
"self": 0.712518634999924
}
}
},
"_update_policy": {
"total": 139.48426841299874,
"count": 136,
"self": 56.072969266988366,
"children": {
"TorchPPOOptimizer.update": {
"total": 83.41129914601038,
"count": 6933,
"self": 83.41129914601038
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.920001164369751e-07,
"count": 1,
"self": 8.920001164369751e-07
},
"TrainerController._save_models": {
"total": 0.09132548399998086,
"count": 1,
"self": 0.0011502849999942555,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0901751989999866,
"count": 1,
"self": 0.0901751989999866
}
}
}
}
}
}
}