ppo-Huggy / run_logs /timers.json
SimAQS's picture
Huggy
00a14ee verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4032227993011475,
"min": 1.4032227993011475,
"max": 1.4250636100769043,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70273.3984375,
"min": 31750.2421875,
"max": 72666.2890625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 82.46243739565944,
"min": 79.85922330097087,
"max": 345.09722222222223,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49395.0,
"min": 17735.0,
"max": 49980.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999933.0,
"min": 49902.0,
"max": 1999933.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999933.0,
"min": 49902.0,
"max": 1999933.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.480181932449341,
"min": -0.0228869765996933,
"max": 2.480181932449341,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1485.62890625,
"min": -1.1672358512878418,
"max": 1485.62890625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8360012725916053,
"min": 1.9109999584216697,
"max": 3.969532559552324,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2297.7647622823715,
"min": 97.46099787950516,
"max": 2367.4904720783234,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8360012725916053,
"min": 1.9109999584216697,
"max": 3.969532559552324,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2297.7647622823715,
"min": 97.46099787950516,
"max": 2367.4904720783234,
"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": 0.0204498616309138,
"min": 0.014118269294461545,
"max": 0.02110763323532107,
"count": 39
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0408997232618276,
"min": 0.02823653858892309,
"max": 0.056355524228032056,
"count": 39
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06101755319784084,
"min": 0.025329673849046233,
"max": 0.06452957457966274,
"count": 39
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.12203510639568169,
"min": 0.050659347698092466,
"max": 0.19358872373898822,
"count": 39
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.637148787650004e-06,
"min": 3.637148787650004e-06,
"max": 0.000288906003698,
"count": 39
},
"Huggy.Policy.LearningRate.sum": {
"value": 7.274297575300008e-06,
"min": 7.274297575300008e-06,
"max": 0.000866718011094,
"count": 39
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10121235,
"min": 0.10121235,
"max": 0.19630200000000006,
"count": 39
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.2024247,
"min": 0.2024247,
"max": 0.5889060000000002,
"count": 39
},
"Huggy.Policy.Beta.mean": {
"value": 7.049626500000005e-05,
"min": 7.049626500000005e-05,
"max": 0.004815469799999999,
"count": 39
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001409925300000001,
"min": 0.0001409925300000001,
"max": 0.014446409399999997,
"count": 39
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1749126950",
"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": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1749129277"
},
"total": 2327.6585178170003,
"count": 1,
"self": 0.4243857430001299,
"children": {
"run_training.setup": {
"total": 0.020493371000156912,
"count": 1,
"self": 0.020493371000156912
},
"TrainerController.start_learning": {
"total": 2327.213638703,
"count": 1,
"self": 3.971376018931551,
"children": {
"TrainerController._reset_env": {
"total": 2.695449536000069,
"count": 1,
"self": 2.695449536000069
},
"TrainerController.advance": {
"total": 2320.4422704690687,
"count": 228873,
"self": 4.17447375416441,
"children": {
"env_step": {
"total": 1843.4074365249867,
"count": 228873,
"self": 1440.740651961969,
"children": {
"SubprocessEnvManager._take_step": {
"total": 400.06940931801864,
"count": 228873,
"self": 15.114241932868481,
"children": {
"TorchPolicy.evaluate": {
"total": 384.95516738515016,
"count": 219345,
"self": 384.95516738515016
}
}
},
"workers": {
"total": 2.597375244999057,
"count": 228873,
"self": 0.0,
"children": {
"worker_root": {
"total": 2320.482950896052,
"count": 228873,
"is_parallel": true,
"self": 1143.13266930412,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.000875411999913922,
"count": 1,
"is_parallel": true,
"self": 0.0002583030000096187,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006171089999043033,
"count": 2,
"is_parallel": true,
"self": 0.0006171089999043033
}
}
},
"UnityEnvironment.step": {
"total": 0.06980103900014001,
"count": 1,
"is_parallel": true,
"self": 0.00026880599989453913,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020001900020361063,
"count": 1,
"is_parallel": true,
"self": 0.00020001900020361063
},
"communicator.exchange": {
"total": 0.057674432000112574,
"count": 1,
"is_parallel": true,
"self": 0.057674432000112574
},
"steps_from_proto": {
"total": 0.011657781999929284,
"count": 1,
"is_parallel": true,
"self": 0.00021883499994146405,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.01143894699998782,
"count": 2,
"is_parallel": true,
"self": 0.01143894699998782
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1177.350281591932,
"count": 228872,
"is_parallel": true,
"self": 35.26537058388294,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 77.41046027703169,
"count": 228872,
"is_parallel": true,
"self": 77.41046027703169
},
"communicator.exchange": {
"total": 982.0881562039654,
"count": 228872,
"is_parallel": true,
"self": 982.0881562039654
},
"steps_from_proto": {
"total": 82.5862945270519,
"count": 228872,
"is_parallel": true,
"self": 28.992258894847964,
"children": {
"_process_rank_one_or_two_observation": {
"total": 53.59403563220394,
"count": 457744,
"is_parallel": true,
"self": 53.59403563220394
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 472.8603601899176,
"count": 228873,
"self": 5.954229855828089,
"children": {
"process_trajectory": {
"total": 156.19246266808796,
"count": 228873,
"self": 155.027612567088,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1648501009999563,
"count": 10,
"self": 1.1648501009999563
}
}
},
"_update_policy": {
"total": 310.7136676660016,
"count": 95,
"self": 246.77821818201664,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.93544948398494,
"count": 2850,
"self": 63.93544948398494
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.200002750731073e-07,
"count": 1,
"self": 9.200002750731073e-07
},
"TrainerController._save_models": {
"total": 0.1045417589994031,
"count": 1,
"self": 0.0023716699997748947,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1021700889996282,
"count": 1,
"self": 0.1021700889996282
}
}
}
}
}
}
}