ppo-Huggy / run_logs /timers.json
andman's picture
Huggy
86aa591 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.405800223350525,
"min": 1.405800223350525,
"max": 1.4281845092773438,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70893.1015625,
"min": 34271.07421875,
"max": 73581.7890625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 99.12825651302605,
"min": 91.81632653061224,
"max": 345.68531468531467,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49465.0,
"min": 20653.0,
"max": 50201.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999940.0,
"min": 49888.0,
"max": 1999940.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999940.0,
"min": 49888.0,
"max": 1999940.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3598928451538086,
"min": 0.06931767612695694,
"max": 2.425286293029785,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1177.5865478515625,
"min": 4.297696113586426,
"max": 1268.14013671875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6092003543295696,
"min": 1.8397609197324323,
"max": 3.884042072676309,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1800.9909768104553,
"min": 114.0651770234108,
"max": 1934.1142175793648,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6092003543295696,
"min": 1.8397609197324323,
"max": 3.884042072676309,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1800.9909768104553,
"min": 114.0651770234108,
"max": 1934.1142175793648,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.018317702404844264,
"min": 0.014172436327983935,
"max": 0.019498834006501257,
"count": 39
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03663540480968853,
"min": 0.02834487265596787,
"max": 0.05849650201950377,
"count": 39
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05236370377242565,
"min": 0.022220978658232426,
"max": 0.06053369268774986,
"count": 39
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1047274075448513,
"min": 0.05355641475568215,
"max": 0.17974315633376436,
"count": 39
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.435623854824994e-06,
"min": 3.435623854824994e-06,
"max": 0.00028930750356416664,
"count": 39
},
"Huggy.Policy.LearningRate.sum": {
"value": 6.871247709649988e-06,
"min": 6.871247709649988e-06,
"max": 0.0008679225106924999,
"count": 39
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10114517499999998,
"min": 0.10114517499999998,
"max": 0.19643583333333337,
"count": 39
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20229034999999995,
"min": 0.20229034999999995,
"max": 0.5893075000000001,
"count": 39
},
"Huggy.Policy.Beta.mean": {
"value": 6.71442324999999e-05,
"min": 6.71442324999999e-05,
"max": 0.004822148083333334,
"count": 39
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001342884649999998,
"min": 0.0001342884649999998,
"max": 0.014466444250000002,
"count": 39
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1740412487",
"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/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics --resume",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1740414952"
},
"total": 2465.298559881,
"count": 1,
"self": 0.7643519220005146,
"children": {
"run_training.setup": {
"total": 0.02765989499994248,
"count": 1,
"self": 0.02765989499994248
},
"TrainerController.start_learning": {
"total": 2464.5065480639996,
"count": 1,
"self": 4.425900453118629,
"children": {
"TrainerController._reset_env": {
"total": 2.4853436050000255,
"count": 1,
"self": 2.4853436050000255
},
"TrainerController.advance": {
"total": 2457.435223551881,
"count": 228113,
"self": 4.540100687677295,
"children": {
"env_step": {
"total": 1992.533555223055,
"count": 228113,
"self": 1560.5688310781504,
"children": {
"SubprocessEnvManager._take_step": {
"total": 429.26938503792564,
"count": 228113,
"self": 15.986469289972092,
"children": {
"TorchPolicy.evaluate": {
"total": 413.28291574795355,
"count": 219724,
"self": 413.28291574795355
}
}
},
"workers": {
"total": 2.6953391069788495,
"count": 228113,
"self": 0.0,
"children": {
"worker_root": {
"total": 2456.9563010259412,
"count": 228113,
"is_parallel": true,
"self": 1184.490125997812,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010660250000000815,
"count": 1,
"is_parallel": true,
"self": 0.00029705299994020606,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007689720000598754,
"count": 2,
"is_parallel": true,
"self": 0.0007689720000598754
}
}
},
"UnityEnvironment.step": {
"total": 0.031171154000048773,
"count": 1,
"is_parallel": true,
"self": 0.0002881180000713357,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020092099998691992,
"count": 1,
"is_parallel": true,
"self": 0.00020092099998691992
},
"communicator.exchange": {
"total": 0.02985740999997688,
"count": 1,
"is_parallel": true,
"self": 0.02985740999997688
},
"steps_from_proto": {
"total": 0.0008247050000136369,
"count": 1,
"is_parallel": true,
"self": 0.00019122699995932635,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006334780000543105,
"count": 2,
"is_parallel": true,
"self": 0.0006334780000543105
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1272.4661750281293,
"count": 228112,
"is_parallel": true,
"self": 36.526257666087076,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 83.60656872903655,
"count": 228112,
"is_parallel": true,
"self": 83.60656872903655
},
"communicator.exchange": {
"total": 1063.6964288429965,
"count": 228112,
"is_parallel": true,
"self": 1063.6964288429965
},
"steps_from_proto": {
"total": 88.63691979000919,
"count": 228112,
"is_parallel": true,
"self": 32.75271945910265,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.88420033090654,
"count": 456224,
"is_parallel": true,
"self": 55.88420033090654
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 460.3615676411488,
"count": 228113,
"self": 6.240061821120889,
"children": {
"process_trajectory": {
"total": 159.4356608720284,
"count": 228113,
"self": 157.9516702440285,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4839906279999013,
"count": 10,
"self": 1.4839906279999013
}
}
},
"_update_policy": {
"total": 294.6858449479995,
"count": 95,
"self": 232.57455055200796,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.111294395991536,
"count": 2850,
"self": 62.111294395991536
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.229000190505758e-06,
"count": 1,
"self": 1.229000190505758e-06
},
"TrainerController._save_models": {
"total": 0.16007922500011773,
"count": 1,
"self": 0.0038889319998816063,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15619029300023612,
"count": 1,
"self": 0.15619029300023612
}
}
}
}
}
}
}