ppo-Huggy1 / run_logs /timers.json
joseph-supples's picture
Huggy
3035617
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4080759286880493,
"min": 1.4080759286880493,
"max": 1.4274170398712158,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71628.8203125,
"min": 68926.96875,
"max": 77251.875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 93.93371212121212,
"min": 83.39629005059022,
"max": 399.736,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49597.0,
"min": 48895.0,
"max": 50036.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999976.0,
"min": 49664.0,
"max": 1999976.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999976.0,
"min": 49664.0,
"max": 1999976.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.388129711151123,
"min": 0.15435443818569183,
"max": 2.4616634845733643,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1260.9324951171875,
"min": 19.139949798583984,
"max": 1412.994873046875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6803636244977964,
"min": 1.8633846055355765,
"max": 3.971421940848366,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1943.2319937348366,
"min": 231.05969108641148,
"max": 2306.3570937514305,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6803636244977964,
"min": 1.8633846055355765,
"max": 3.971421940848366,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1943.2319937348366,
"min": 231.05969108641148,
"max": 2306.3570937514305,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01851713909838711,
"min": 0.014175409950702387,
"max": 0.02052046923957328,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05555141729516133,
"min": 0.030003290664171803,
"max": 0.061561407718719846,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05122846989995903,
"min": 0.021046641779442626,
"max": 0.05711060663064321,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1536854096998771,
"min": 0.04209328355888525,
"max": 0.16330549667278926,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.3907988697666582e-06,
"min": 3.3907988697666582e-06,
"max": 0.00029536207654597504,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0172396609299974e-05,
"min": 1.0172396609299974e-05,
"max": 0.0008440102686632501,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1011302333333333,
"min": 0.1011302333333333,
"max": 0.19845402500000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3033906999999999,
"min": 0.20744535000000003,
"max": 0.58133675,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.639864333333318e-05,
"min": 6.639864333333318e-05,
"max": 0.004922855847499998,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019919592999999953,
"min": 0.00019919592999999953,
"max": 0.014068703824999997,
"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": "1680819405",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1680821868"
},
"total": 2462.815861168,
"count": 1,
"self": 0.44491818099959346,
"children": {
"run_training.setup": {
"total": 0.11981249600000865,
"count": 1,
"self": 0.11981249600000865
},
"TrainerController.start_learning": {
"total": 2462.2511304910004,
"count": 1,
"self": 4.538146607994804,
"children": {
"TrainerController._reset_env": {
"total": 3.913595823000037,
"count": 1,
"self": 3.913595823000037
},
"TrainerController.advance": {
"total": 2453.6743613350054,
"count": 232273,
"self": 5.008647215911424,
"children": {
"env_step": {
"total": 1928.4490272980775,
"count": 232273,
"self": 1631.9802001250118,
"children": {
"SubprocessEnvManager._take_step": {
"total": 293.4689074569941,
"count": 232273,
"self": 17.73792373494564,
"children": {
"TorchPolicy.evaluate": {
"total": 275.73098372204845,
"count": 223036,
"self": 275.73098372204845
}
}
},
"workers": {
"total": 2.9999197160714175,
"count": 232273,
"self": 0.0,
"children": {
"worker_root": {
"total": 2453.645232148015,
"count": 232273,
"is_parallel": true,
"self": 1120.5050825170536,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011839300000247022,
"count": 1,
"is_parallel": true,
"self": 0.0004098560001466467,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007740739998780555,
"count": 2,
"is_parallel": true,
"self": 0.0007740739998780555
}
}
},
"UnityEnvironment.step": {
"total": 0.04417618499996934,
"count": 1,
"is_parallel": true,
"self": 0.0003496950000680954,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002362599999514714,
"count": 1,
"is_parallel": true,
"self": 0.0002362599999514714
},
"communicator.exchange": {
"total": 0.0428062900000441,
"count": 1,
"is_parallel": true,
"self": 0.0428062900000441
},
"steps_from_proto": {
"total": 0.0007839399999056695,
"count": 1,
"is_parallel": true,
"self": 0.00023921999979847897,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005447200001071906,
"count": 2,
"is_parallel": true,
"self": 0.0005447200001071906
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1333.1401496309616,
"count": 232272,
"is_parallel": true,
"self": 39.28310855706877,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 86.0830989339363,
"count": 232272,
"is_parallel": true,
"self": 86.0830989339363
},
"communicator.exchange": {
"total": 1114.2749036199848,
"count": 232272,
"is_parallel": true,
"self": 1114.2749036199848
},
"steps_from_proto": {
"total": 93.49903851997169,
"count": 232272,
"is_parallel": true,
"self": 37.44816701091054,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.05087150906115,
"count": 464544,
"is_parallel": true,
"self": 56.05087150906115
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 520.2166868210165,
"count": 232273,
"self": 7.029489335897779,
"children": {
"process_trajectory": {
"total": 139.2390641081189,
"count": 232273,
"self": 137.87220489012043,
"children": {
"RLTrainer._checkpoint": {
"total": 1.366859217998467,
"count": 10,
"self": 1.366859217998467
}
}
},
"_update_policy": {
"total": 373.94813337699986,
"count": 97,
"self": 315.0311455779964,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.91698779900344,
"count": 2910,
"self": 58.91698779900344
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.990000424091704e-07,
"count": 1,
"self": 8.990000424091704e-07
},
"TrainerController._save_models": {
"total": 0.12502582600018286,
"count": 1,
"self": 0.0023226990001603554,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1227031270000225,
"count": 1,
"self": 0.1227031270000225
}
}
}
}
}
}
}