ppo-Huggy / run_logs /timers.json
DenCT's picture
Huggy
03d30f3
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4002013206481934,
"min": 1.4002013206481934,
"max": 1.4255424737930298,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69604.0078125,
"min": 66782.1875,
"max": 76687.9609375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 101.51829268292683,
"min": 87.37809187279152,
"max": 372.35555555555555,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49947.0,
"min": 48933.0,
"max": 50268.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999699.0,
"min": 49930.0,
"max": 1999699.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999699.0,
"min": 49930.0,
"max": 1999699.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3995072841644287,
"min": 0.01601565070450306,
"max": 2.442922353744507,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1180.5576171875,
"min": 2.146097183227539,
"max": 1361.118896484375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.5885320575983544,
"min": 1.826743610981685,
"max": 3.8605702030927613,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1765.5577723383904,
"min": 244.7836438715458,
"max": 2124.0248813033104,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.5885320575983544,
"min": 1.826743610981685,
"max": 3.8605702030927613,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1765.5577723383904,
"min": 244.7836438715458,
"max": 2124.0248813033104,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016269901224586648,
"min": 0.012794400203711122,
"max": 0.02085149112487367,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04880970367375994,
"min": 0.025588800407422244,
"max": 0.05600049776645999,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.050168426872955425,
"min": 0.024372701129565636,
"max": 0.06093207283152475,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15050528061886628,
"min": 0.04874540225913127,
"max": 0.18279621849457425,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.169798943433331e-06,
"min": 3.169798943433331e-06,
"max": 0.00029525805158065,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.509396830299992e-06,
"min": 9.509396830299992e-06,
"max": 0.0008435017688327498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10105656666666664,
"min": 0.10105656666666664,
"max": 0.19841935000000005,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30316969999999993,
"min": 0.20724939999999994,
"max": 0.58116725,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.272267666666661e-05,
"min": 6.272267666666661e-05,
"max": 0.004921125565000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00018816802999999986,
"min": 0.00018816802999999986,
"max": 0.014060245775,
"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": "1700918920",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1700921509"
},
"total": 2588.717243316,
"count": 1,
"self": 0.6590062359996409,
"children": {
"run_training.setup": {
"total": 0.04301059199997326,
"count": 1,
"self": 0.04301059199997326
},
"TrainerController.start_learning": {
"total": 2588.0152264880003,
"count": 1,
"self": 4.831478121928285,
"children": {
"TrainerController._reset_env": {
"total": 9.193313670999999,
"count": 1,
"self": 9.193313670999999
},
"TrainerController.advance": {
"total": 2573.839827571072,
"count": 232046,
"self": 5.07291649607987,
"children": {
"env_step": {
"total": 2050.7720517089792,
"count": 232046,
"self": 1688.843354549916,
"children": {
"SubprocessEnvManager._take_step": {
"total": 358.79884253005105,
"count": 232046,
"self": 17.672900061914504,
"children": {
"TorchPolicy.evaluate": {
"total": 341.12594246813654,
"count": 222948,
"self": 341.12594246813654
}
}
},
"workers": {
"total": 3.1298546290121294,
"count": 232046,
"self": 0.0,
"children": {
"worker_root": {
"total": 2580.044296326066,
"count": 232046,
"is_parallel": true,
"self": 1213.2476115000559,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008173410000154036,
"count": 1,
"is_parallel": true,
"self": 0.00024232300000903706,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005750180000063665,
"count": 2,
"is_parallel": true,
"self": 0.0005750180000063665
}
}
},
"UnityEnvironment.step": {
"total": 0.03060772799994993,
"count": 1,
"is_parallel": true,
"self": 0.00031546799993975583,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00017523000002483968,
"count": 1,
"is_parallel": true,
"self": 0.00017523000002483968
},
"communicator.exchange": {
"total": 0.029366025000001628,
"count": 1,
"is_parallel": true,
"self": 0.029366025000001628
},
"steps_from_proto": {
"total": 0.0007510049999837065,
"count": 1,
"is_parallel": true,
"self": 0.000202986999966015,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005480180000176915,
"count": 2,
"is_parallel": true,
"self": 0.0005480180000176915
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1366.7966848260103,
"count": 232045,
"is_parallel": true,
"self": 40.75775970308905,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 88.54931281094315,
"count": 232045,
"is_parallel": true,
"self": 88.54931281094315
},
"communicator.exchange": {
"total": 1142.8307964709816,
"count": 232045,
"is_parallel": true,
"self": 1142.8307964709816
},
"steps_from_proto": {
"total": 94.65881584099668,
"count": 232045,
"is_parallel": true,
"self": 35.33983183411448,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.318984006882204,
"count": 464090,
"is_parallel": true,
"self": 59.318984006882204
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 517.9948593660126,
"count": 232046,
"self": 7.1499879120081005,
"children": {
"process_trajectory": {
"total": 165.86020573200517,
"count": 232046,
"self": 164.61323003000473,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2469757020004408,
"count": 10,
"self": 1.2469757020004408
}
}
},
"_update_policy": {
"total": 344.98466572199936,
"count": 97,
"self": 281.25472827898744,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.72993744301192,
"count": 2910,
"self": 63.72993744301192
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1580000318645034e-06,
"count": 1,
"self": 1.1580000318645034e-06
},
"TrainerController._save_models": {
"total": 0.15060596600005738,
"count": 1,
"self": 0.002873617000204831,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14773234899985255,
"count": 1,
"self": 0.14773234899985255
}
}
}
}
}
}
}