ppo-Huggy / run_logs /timers.json
kparker's picture
Huggy
a85d1e1
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4011348485946655,
"min": 1.4011348485946655,
"max": 1.4277105331420898,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 67781.296875,
"min": 67781.296875,
"max": 78317.140625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 89.74542124542124,
"min": 70.70773638968481,
"max": 370.4632352941176,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49001.0,
"min": 49001.0,
"max": 50383.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999936.0,
"min": 49769.0,
"max": 1999936.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999936.0,
"min": 49769.0,
"max": 1999936.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4222004413604736,
"min": 0.1469631940126419,
"max": 2.5127413272857666,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1322.521484375,
"min": 19.840030670166016,
"max": 1687.376220703125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.63819289687789,
"min": 1.6920575512780083,
"max": 4.138283928603302,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1986.4533216953278,
"min": 228.42776942253113,
"max": 2724.2467193603516,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.63819289687789,
"min": 1.6920575512780083,
"max": 4.138283928603302,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1986.4533216953278,
"min": 228.42776942253113,
"max": 2724.2467193603516,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015229934932358446,
"min": 0.013656420340582068,
"max": 0.019541097444744082,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04568980479707534,
"min": 0.027312840681164137,
"max": 0.058497190518149486,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.052848895059691536,
"min": 0.020886354044907626,
"max": 0.05984806766112646,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1585466851790746,
"min": 0.04300788020094236,
"max": 0.1678674644480149,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5616488128166693e-06,
"min": 3.5616488128166693e-06,
"max": 0.00029528167657277507,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0684946438450008e-05,
"min": 1.0684946438450008e-05,
"max": 0.0008440567686477499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10118718333333336,
"min": 0.10118718333333336,
"max": 0.19842722500000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30356155000000007,
"min": 0.20757504999999998,
"max": 0.5813522500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.924044833333337e-05,
"min": 6.924044833333337e-05,
"max": 0.0049215185275,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002077213450000001,
"min": 0.0002077213450000001,
"max": 0.014069477274999999,
"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": "1674041826",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1674044031"
},
"total": 2205.542946817,
"count": 1,
"self": 0.38941497199994046,
"children": {
"run_training.setup": {
"total": 0.11048647799998434,
"count": 1,
"self": 0.11048647799998434
},
"TrainerController.start_learning": {
"total": 2205.043045367,
"count": 1,
"self": 4.215791454017108,
"children": {
"TrainerController._reset_env": {
"total": 10.201900758000079,
"count": 1,
"self": 10.201900758000079
},
"TrainerController.advance": {
"total": 2190.518082815983,
"count": 232986,
"self": 4.114449961973605,
"children": {
"env_step": {
"total": 1732.1122767110385,
"count": 232986,
"self": 1453.2506764581544,
"children": {
"SubprocessEnvManager._take_step": {
"total": 276.2997106958942,
"count": 232986,
"self": 14.413934111025583,
"children": {
"TorchPolicy.evaluate": {
"total": 261.8857765848686,
"count": 222968,
"self": 64.41294918790959,
"children": {
"TorchPolicy.sample_actions": {
"total": 197.47282739695902,
"count": 222968,
"self": 197.47282739695902
}
}
}
}
},
"workers": {
"total": 2.561889556989854,
"count": 232986,
"self": 0.0,
"children": {
"worker_root": {
"total": 2197.3325989559726,
"count": 232986,
"is_parallel": true,
"self": 998.0425907898161,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0019036700000469864,
"count": 1,
"is_parallel": true,
"self": 0.0003006559999221281,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016030140001248583,
"count": 2,
"is_parallel": true,
"self": 0.0016030140001248583
}
}
},
"UnityEnvironment.step": {
"total": 0.02741353800001889,
"count": 1,
"is_parallel": true,
"self": 0.0002875500003938214,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001829599998472986,
"count": 1,
"is_parallel": true,
"self": 0.0001829599998472986
},
"communicator.exchange": {
"total": 0.026205667999875004,
"count": 1,
"is_parallel": true,
"self": 0.026205667999875004
},
"steps_from_proto": {
"total": 0.0007373599999027647,
"count": 1,
"is_parallel": true,
"self": 0.00023956299992278218,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004977969999799825,
"count": 2,
"is_parallel": true,
"self": 0.0004977969999799825
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1199.2900081661564,
"count": 232985,
"is_parallel": true,
"self": 34.70218929501607,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 73.61232741704112,
"count": 232985,
"is_parallel": true,
"self": 73.61232741704112
},
"communicator.exchange": {
"total": 986.2214086790295,
"count": 232985,
"is_parallel": true,
"self": 986.2214086790295
},
"steps_from_proto": {
"total": 104.75408277506972,
"count": 232985,
"is_parallel": true,
"self": 37.83890844519783,
"children": {
"_process_rank_one_or_two_observation": {
"total": 66.91517432987189,
"count": 465970,
"is_parallel": true,
"self": 66.91517432987189
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 454.2913561429707,
"count": 232986,
"self": 6.237994273992172,
"children": {
"process_trajectory": {
"total": 149.18976241797964,
"count": 232986,
"self": 148.10407795297965,
"children": {
"RLTrainer._checkpoint": {
"total": 1.0856844649999857,
"count": 10,
"self": 1.0856844649999857
}
}
},
"_update_policy": {
"total": 298.8635994509989,
"count": 97,
"self": 245.89236900199649,
"children": {
"TorchPPOOptimizer.update": {
"total": 52.971230449002405,
"count": 2910,
"self": 52.971230449002405
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.035999957821332e-06,
"count": 1,
"self": 1.035999957821332e-06
},
"TrainerController._save_models": {
"total": 0.10726930300006643,
"count": 1,
"self": 0.002165169999898353,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10510413300016808,
"count": 1,
"self": 0.10510413300016808
}
}
}
}
}
}
}