ppo-Huggy / run_logs /timers.json
jules654's picture
Huggy
dca92f1
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4164135456085205,
"min": 1.4164135456085205,
"max": 1.4309824705123901,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 72425.4765625,
"min": 69325.21875,
"max": 76602.671875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 81.3479674796748,
"min": 81.3479674796748,
"max": 387.5736434108527,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 50029.0,
"min": 48932.0,
"max": 50029.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999992.0,
"min": 49377.0,
"max": 1999992.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999992.0,
"min": 49377.0,
"max": 1999992.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.448777437210083,
"min": 0.12019020318984985,
"max": 2.474571943283081,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1505.9981689453125,
"min": 15.384346008300781,
"max": 1505.9981689453125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7789531511989067,
"min": 1.942840071162209,
"max": 3.928511282212192,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2324.0561879873276,
"min": 248.68352910876274,
"max": 2324.0561879873276,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7789531511989067,
"min": 1.942840071162209,
"max": 3.928511282212192,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2324.0561879873276,
"min": 248.68352910876274,
"max": 2324.0561879873276,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01703536279092077,
"min": 0.013220861369093957,
"max": 0.020258093502151398,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.051106088372762315,
"min": 0.026441722738187914,
"max": 0.06077428050645419,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0654639565696319,
"min": 0.021373123830805224,
"max": 0.0654639565696319,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1963918697088957,
"min": 0.04274624766161045,
"max": 0.1963918697088957,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.402148865983324e-06,
"min": 3.402148865983324e-06,
"max": 0.000295362526545825,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0206446597949972e-05,
"min": 1.0206446597949972e-05,
"max": 0.0008442519185826997,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1011340166666667,
"min": 0.1011340166666667,
"max": 0.19845417499999995,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3034020500000001,
"min": 0.20740310000000003,
"max": 0.5814173,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.65874316666665e-05,
"min": 6.65874316666665e-05,
"max": 0.004922863332499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001997622949999995,
"min": 0.0001997622949999995,
"max": 0.014072723269999995,
"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": "1683665340",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1683667846"
},
"total": 2506.51184806,
"count": 1,
"self": 0.48524509600019883,
"children": {
"run_training.setup": {
"total": 0.04226491500003249,
"count": 1,
"self": 0.04226491500003249
},
"TrainerController.start_learning": {
"total": 2505.9843380489997,
"count": 1,
"self": 4.806820299042101,
"children": {
"TrainerController._reset_env": {
"total": 4.097878666000042,
"count": 1,
"self": 4.097878666000042
},
"TrainerController.advance": {
"total": 2496.950023947957,
"count": 232127,
"self": 4.697687820901592,
"children": {
"env_step": {
"total": 1959.0550387990252,
"count": 232127,
"self": 1658.7967406081575,
"children": {
"SubprocessEnvManager._take_step": {
"total": 297.3623610469258,
"count": 232127,
"self": 17.643036736952354,
"children": {
"TorchPolicy.evaluate": {
"total": 279.71932430997344,
"count": 223036,
"self": 279.71932430997344
}
}
},
"workers": {
"total": 2.8959371439419783,
"count": 232127,
"self": 0.0,
"children": {
"worker_root": {
"total": 2497.7259019769235,
"count": 232127,
"is_parallel": true,
"self": 1141.259819717966,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011063800000101764,
"count": 1,
"is_parallel": true,
"self": 0.00039531199990960886,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007110680001005676,
"count": 2,
"is_parallel": true,
"self": 0.0007110680001005676
}
}
},
"UnityEnvironment.step": {
"total": 0.030399209999927734,
"count": 1,
"is_parallel": true,
"self": 0.0003344030000107523,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021450899998853856,
"count": 1,
"is_parallel": true,
"self": 0.00021450899998853856
},
"communicator.exchange": {
"total": 0.029081227999995463,
"count": 1,
"is_parallel": true,
"self": 0.029081227999995463
},
"steps_from_proto": {
"total": 0.0007690699999329809,
"count": 1,
"is_parallel": true,
"self": 0.0002585869999620627,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005104829999709182,
"count": 2,
"is_parallel": true,
"self": 0.0005104829999709182
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1356.4660822589576,
"count": 232126,
"is_parallel": true,
"self": 39.174300595768955,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 84.41031769004007,
"count": 232126,
"is_parallel": true,
"self": 84.41031769004007
},
"communicator.exchange": {
"total": 1136.1543269850727,
"count": 232126,
"is_parallel": true,
"self": 1136.1543269850727
},
"steps_from_proto": {
"total": 96.72713698807593,
"count": 232126,
"is_parallel": true,
"self": 38.00443080319235,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.72270618488358,
"count": 464252,
"is_parallel": true,
"self": 58.72270618488358
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 533.1972973280303,
"count": 232127,
"self": 7.010274647014626,
"children": {
"process_trajectory": {
"total": 142.07253350501685,
"count": 232127,
"self": 140.6403547960175,
"children": {
"RLTrainer._checkpoint": {
"total": 1.432178708999345,
"count": 10,
"self": 1.432178708999345
}
}
},
"_update_policy": {
"total": 384.11448917599887,
"count": 97,
"self": 323.7656764150072,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.34881276099168,
"count": 2910,
"self": 60.34881276099168
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0670000847312622e-06,
"count": 1,
"self": 1.0670000847312622e-06
},
"TrainerController._save_models": {
"total": 0.12961406900012662,
"count": 1,
"self": 0.0021546500001932145,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1274594189999334,
"count": 1,
"self": 0.1274594189999334
}
}
}
}
}
}
}