cidanta's picture
First Push
71f2e10 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9183356761932373,
"min": 0.9183356761932373,
"max": 2.8495585918426514,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8727.8623046875,
"min": 8727.8623046875,
"max": 29088.29296875,
"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": 13.193851470947266,
"min": 0.3269372880458832,
"max": 13.193851470947266,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2572.801025390625,
"min": 63.09889602661133,
"max": 2671.29736328125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06785760872926581,
"min": 0.06597045305614159,
"max": 0.0762030234347513,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27143043491706326,
"min": 0.2651096904221192,
"max": 0.37574501045552705,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20179806934560046,
"min": 0.13429099077121448,
"max": 0.28978294513973535,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8071922773824018,
"min": 0.5371639630848579,
"max": 1.370983516760901,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 7.98609733800001e-06,
"min": 7.98609733800001e-06,
"max": 0.00029178600273799997,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.194438935200004e-05,
"min": 3.194438935200004e-05,
"max": 0.00138468003844,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.102662,
"min": 0.102662,
"max": 0.19726200000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.410648,
"min": 0.410648,
"max": 0.96156,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00014283380000000017,
"min": 0.00014283380000000017,
"max": 0.0048633738,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005713352000000007,
"min": 0.0005713352000000007,
"max": 0.023081844,
"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": 25.704545454545453,
"min": 3.659090909090909,
"max": 26.072727272727274,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1131.0,
"min": 161.0,
"max": 1434.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.704545454545453,
"min": 3.659090909090909,
"max": 26.072727272727274,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1131.0,
"min": 161.0,
"max": 1434.0,
"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": "1745669724",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/home/dj7111/anaconda3/envs/drl_unit5/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics --resume",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1745669933"
},
"total": 208.57703469600528,
"count": 1,
"self": 0.16756878701562528,
"children": {
"run_training.setup": {
"total": 0.009996669992688112,
"count": 1,
"self": 0.009996669992688112
},
"TrainerController.start_learning": {
"total": 208.39946923899697,
"count": 1,
"self": 0.17046460753772408,
"children": {
"TrainerController._reset_env": {
"total": 1.4206229030096438,
"count": 1,
"self": 1.4206229030096438
},
"TrainerController.advance": {
"total": 206.75449016444327,
"count": 18192,
"self": 0.15516610124905128,
"children": {
"env_step": {
"total": 136.26287835265975,
"count": 18192,
"self": 82.56458374521753,
"children": {
"SubprocessEnvManager._take_step": {
"total": 53.592016111841076,
"count": 18192,
"self": 0.5494703180884244,
"children": {
"TorchPolicy.evaluate": {
"total": 53.04254579375265,
"count": 18192,
"self": 53.04254579375265
}
}
},
"workers": {
"total": 0.10627849560114555,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 207.97136293462245,
"count": 18192,
"is_parallel": true,
"self": 135.74071201484185,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010651019983924925,
"count": 1,
"is_parallel": true,
"self": 0.00034082902129739523,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007242729770950973,
"count": 10,
"is_parallel": true,
"self": 0.0007242729770950973
}
}
},
"UnityEnvironment.step": {
"total": 0.011852554001961835,
"count": 1,
"is_parallel": true,
"self": 0.000139130002935417,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00014864900731481612,
"count": 1,
"is_parallel": true,
"self": 0.00014864900731481612
},
"communicator.exchange": {
"total": 0.011153054991154931,
"count": 1,
"is_parallel": true,
"self": 0.011153054991154931
},
"steps_from_proto": {
"total": 0.00041172000055667013,
"count": 1,
"is_parallel": true,
"self": 0.00010965198453050107,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00030206801602616906,
"count": 10,
"is_parallel": true,
"self": 0.00030206801602616906
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 72.2306509197806,
"count": 18191,
"is_parallel": true,
"self": 2.1156271115178242,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 1.2828514170396375,
"count": 18191,
"is_parallel": true,
"self": 1.2828514170396375
},
"communicator.exchange": {
"total": 62.73566267610295,
"count": 18191,
"is_parallel": true,
"self": 62.73566267610295
},
"steps_from_proto": {
"total": 6.096509715120192,
"count": 18191,
"is_parallel": true,
"self": 1.4043431620375486,
"children": {
"_process_rank_one_or_two_observation": {
"total": 4.692166553082643,
"count": 181910,
"is_parallel": true,
"self": 4.692166553082643
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 70.33644571053446,
"count": 18192,
"self": 0.21244245399429929,
"children": {
"process_trajectory": {
"total": 14.92974067950854,
"count": 18192,
"self": 14.687909800501075,
"children": {
"RLTrainer._checkpoint": {
"total": 0.24183087900746614,
"count": 4,
"self": 0.24183087900746614
}
}
},
"_update_policy": {
"total": 55.19426257703162,
"count": 90,
"self": 10.670646364364075,
"children": {
"TorchPPOOptimizer.update": {
"total": 44.52361621266755,
"count": 4587,
"self": 44.52361621266755
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.390021786093712e-07,
"count": 1,
"self": 4.390021786093712e-07
},
"TrainerController._save_models": {
"total": 0.05389112500415649,
"count": 1,
"self": 0.0005390110018197447,
"children": {
"RLTrainer._checkpoint": {
"total": 0.05335211400233675,
"count": 1,
"self": 0.05335211400233675
}
}
}
}
}
}
}