zwse's picture
First Push
6cf46a7 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8022259473800659,
"min": 0.8014256954193115,
"max": 2.8670122623443604,
"count": 30
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8242.0693359375,
"min": 7874.4912109375,
"max": 29424.146484375,
"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": 13.173124313354492,
"min": 0.37859639525413513,
"max": 13.173124313354492,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2687.3173828125,
"min": 73.44770050048828,
"max": 2687.3173828125,
"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.Losses.PolicyLoss.mean": {
"value": 0.07067232018480889,
"min": 0.05988469312745591,
"max": 0.07774739522993673,
"count": 30
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.35336160092404445,
"min": 0.2523640542297953,
"max": 0.38873697614968367,
"count": 30
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18895831002908595,
"min": 0.10748483130352243,
"max": 0.3182408903889796,
"count": 30
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9447915501454297,
"min": 0.42993932521408973,
"max": 1.3522001163047905,
"count": 30
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 5.288098237333331e-06,
"min": 5.288098237333331e-06,
"max": 0.00029458800180399996,
"count": 30
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 2.6440491186666655e-05,
"min": 2.6440491186666655e-05,
"max": 0.0014234400255199997,
"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.CumulativeReward.mean": {
"value": 25.745454545454546,
"min": 2.9318181818181817,
"max": 26.054545454545455,
"count": 30
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1416.0,
"min": 129.0,
"max": 1433.0,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.745454545454546,
"min": 2.9318181818181817,
"max": 26.054545454545455,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1416.0,
"min": 129.0,
"max": 1433.0,
"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": "1738479473",
"python_version": "3.10.12 (main, Jan 17 2025, 14:35:34) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1738480365"
},
"total": 891.152744248,
"count": 1,
"self": 0.5941462069998806,
"children": {
"run_training.setup": {
"total": 0.027109445999997206,
"count": 1,
"self": 0.027109445999997206
},
"TrainerController.start_learning": {
"total": 890.5314885950002,
"count": 1,
"self": 1.3352818300062381,
"children": {
"TrainerController._reset_env": {
"total": 3.2812997700000324,
"count": 1,
"self": 3.2812997700000324
},
"TrainerController.advance": {
"total": 885.8248558179938,
"count": 27334,
"self": 0.6407475160152671,
"children": {
"env_step": {
"total": 885.1841083019785,
"count": 27334,
"self": 680.6215272269919,
"children": {
"SubprocessEnvManager._take_step": {
"total": 203.9320988170058,
"count": 27334,
"self": 3.263279962019624,
"children": {
"TorchPolicy.evaluate": {
"total": 200.66881885498617,
"count": 27334,
"self": 200.66881885498617
}
}
},
"workers": {
"total": 0.630482257980816,
"count": 27334,
"self": 0.0,
"children": {
"worker_root": {
"total": 887.6051906909847,
"count": 27334,
"is_parallel": true,
"self": 426.33781024198834,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.010124706999931732,
"count": 1,
"is_parallel": true,
"self": 0.004616591999933917,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.005508114999997815,
"count": 10,
"is_parallel": true,
"self": 0.005508114999997815
}
}
},
"UnityEnvironment.step": {
"total": 0.046826746000078856,
"count": 1,
"is_parallel": true,
"self": 0.0007473220000520087,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004827340000019831,
"count": 1,
"is_parallel": true,
"self": 0.0004827340000019831
},
"communicator.exchange": {
"total": 0.04329625399998349,
"count": 1,
"is_parallel": true,
"self": 0.04329625399998349
},
"steps_from_proto": {
"total": 0.0023004360000413726,
"count": 1,
"is_parallel": true,
"self": 0.0004251870001326097,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001875248999908763,
"count": 10,
"is_parallel": true,
"self": 0.001875248999908763
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 461.2673804489964,
"count": 27333,
"is_parallel": true,
"self": 20.91512882396421,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 11.119012153011226,
"count": 27333,
"is_parallel": true,
"self": 11.119012153011226
},
"communicator.exchange": {
"total": 364.0221805170054,
"count": 27333,
"is_parallel": true,
"self": 364.0221805170054
},
"steps_from_proto": {
"total": 65.21105895501557,
"count": 27333,
"is_parallel": true,
"self": 12.948068008005635,
"children": {
"_process_rank_one_or_two_observation": {
"total": 52.26299094700994,
"count": 273330,
"is_parallel": true,
"self": 52.26299094700994
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0011733970000022964,
"count": 1,
"self": 0.0011733970000022964,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 875.286995382987,
"count": 1179446,
"is_parallel": true,
"self": 27.250773818038738,
"children": {
"process_trajectory": {
"total": 449.79100520894883,
"count": 1179446,
"is_parallel": true,
"self": 448.5130200439488,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2779851650000182,
"count": 6,
"is_parallel": true,
"self": 1.2779851650000182
}
}
},
"_update_policy": {
"total": 398.24521635599945,
"count": 136,
"is_parallel": true,
"self": 106.28471950500784,
"children": {
"TorchPPOOptimizer.update": {
"total": 291.9604968509916,
"count": 6933,
"is_parallel": true,
"self": 291.9604968509916
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08887778000007529,
"count": 1,
"self": 0.0012316460001784435,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08764613399989685,
"count": 1,
"self": 0.08764613399989685
}
}
}
}
}
}
}