ppo-Huggy / run_logs /timers.json
42loops's picture
Huggy
2fe12e1 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.405234932899475,
"min": 1.405234932899475,
"max": 1.4290775060653687,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70105.765625,
"min": 69296.6171875,
"max": 76739.4140625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 98.89021956087825,
"min": 92.55887850467289,
"max": 424.6271186440678,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49544.0,
"min": 49349.0,
"max": 50106.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999957.0,
"min": 49832.0,
"max": 1999957.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999957.0,
"min": 49832.0,
"max": 1999957.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.442089319229126,
"min": 0.03161729499697685,
"max": 2.442669630050659,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1223.4866943359375,
"min": 3.699223518371582,
"max": 1292.591064453125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.87446792611105,
"min": 1.7585089224526005,
"max": 3.959821509823115,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1941.108430981636,
"min": 205.74554392695427,
"max": 2034.9977129101753,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.87446792611105,
"min": 1.7585089224526005,
"max": 3.959821509823115,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1941.108430981636,
"min": 205.74554392695427,
"max": 2034.9977129101753,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016256860780089886,
"min": 0.01403970004224296,
"max": 0.020730538688561256,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04877058234026966,
"min": 0.02807940008448592,
"max": 0.05661840411824717,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.057190127463804356,
"min": 0.02258006970708569,
"max": 0.05952985690285762,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17157038239141306,
"min": 0.04516013941417138,
"max": 0.17737147100269796,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5514988162000037e-06,
"min": 3.5514988162000037e-06,
"max": 0.0002953098015634,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0654496448600011e-05,
"min": 1.0654496448600011e-05,
"max": 0.0008439868686710499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1011838,
"min": 0.1011838,
"max": 0.19843660000000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3035514,
"min": 0.207573,
"max": 0.58132895,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.907162000000006e-05,
"min": 6.907162000000006e-05,
"max": 0.004921986340000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002072148600000002,
"min": 0.0002072148600000002,
"max": 0.014068314605000002,
"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
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1741709347",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/data3/code/learn-ml/ml-agents/local/bin/mlagents-learn ./ml-agents/config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --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": "1741710790"
},
"total": 1443.3108411128633,
"count": 1,
"self": 0.2707518138922751,
"children": {
"run_training.setup": {
"total": 0.01838511321693659,
"count": 1,
"self": 0.01838511321693659
},
"TrainerController.start_learning": {
"total": 1443.021704185754,
"count": 1,
"self": 2.5604317747056484,
"children": {
"TrainerController._reset_env": {
"total": 2.157722111325711,
"count": 1,
"self": 2.157722111325711
},
"TrainerController.advance": {
"total": 1438.1851064418443,
"count": 231845,
"self": 2.4234751788899302,
"children": {
"env_step": {
"total": 1101.257265583612,
"count": 231845,
"self": 849.766101682093,
"children": {
"SubprocessEnvManager._take_step": {
"total": 249.85609805351123,
"count": 231845,
"self": 8.691257696133107,
"children": {
"TorchPolicy.evaluate": {
"total": 241.16484035737813,
"count": 222934,
"self": 241.16484035737813
}
}
},
"workers": {
"total": 1.6350658480077982,
"count": 231845,
"self": 0.0,
"children": {
"worker_root": {
"total": 1438.9018551791087,
"count": 231845,
"is_parallel": true,
"self": 739.8633355968632,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0006203758530318737,
"count": 1,
"is_parallel": true,
"self": 0.0001341588795185089,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004862169735133648,
"count": 2,
"is_parallel": true,
"self": 0.0004862169735133648
}
}
},
"UnityEnvironment.step": {
"total": 0.0162568180821836,
"count": 1,
"is_parallel": true,
"self": 0.00013570860028266907,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00014068931341171265,
"count": 1,
"is_parallel": true,
"self": 0.00014068931341171265
},
"communicator.exchange": {
"total": 0.015543772839009762,
"count": 1,
"is_parallel": true,
"self": 0.015543772839009762
},
"steps_from_proto": {
"total": 0.00043664732947945595,
"count": 1,
"is_parallel": true,
"self": 9.2359259724617e-05,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00034428806975483894,
"count": 2,
"is_parallel": true,
"self": 0.00034428806975483894
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 699.0385195822455,
"count": 231844,
"is_parallel": true,
"self": 19.548182148020715,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 40.73831975553185,
"count": 231844,
"is_parallel": true,
"self": 40.73831975553185
},
"communicator.exchange": {
"total": 595.31306125829,
"count": 231844,
"is_parallel": true,
"self": 595.31306125829
},
"steps_from_proto": {
"total": 43.438956420402974,
"count": 231844,
"is_parallel": true,
"self": 14.385384313762188,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.053572106640786,
"count": 463688,
"is_parallel": true,
"self": 29.053572106640786
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 334.5043656793423,
"count": 231845,
"self": 3.781373642385006,
"children": {
"process_trajectory": {
"total": 109.35977392503992,
"count": 231845,
"self": 108.26210107142106,
"children": {
"RLTrainer._checkpoint": {
"total": 1.0976728536188602,
"count": 10,
"self": 1.0976728536188602
}
}
},
"_update_policy": {
"total": 221.36321811191738,
"count": 97,
"self": 183.28323324164376,
"children": {
"TorchPPOOptimizer.update": {
"total": 38.07998487027362,
"count": 2910,
"self": 38.07998487027362
}
}
}
}
}
}
},
"trainer_threads": {
"total": 6.100162863731384e-07,
"count": 1,
"self": 6.100162863731384e-07
},
"TrainerController._save_models": {
"total": 0.1184432478621602,
"count": 1,
"self": 0.00259957043454051,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1158436774276197,
"count": 1,
"self": 0.1158436774276197
}
}
}
}
}
}
}