ppo-Huggy / run_logs /timers.json
chavicoski's picture
New version with 0.0001 lr
5aee3c8
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3942005634307861,
"min": 1.394197940826416,
"max": 1.4243015050888062,
"count": 100
},
"Huggy.Policy.Entropy.sum": {
"value": 71408.1640625,
"min": 67129.84375,
"max": 78072.9765625,
"count": 100
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 112.84875846501129,
"min": 77.64779874213836,
"max": 411.6967213114754,
"count": 100
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49992.0,
"min": 48709.0,
"max": 50227.0,
"count": 100
},
"Huggy.Step.mean": {
"value": 4999957.0,
"min": 49599.0,
"max": 4999957.0,
"count": 100
},
"Huggy.Step.sum": {
"value": 4999957.0,
"min": 49599.0,
"max": 4999957.0,
"count": 100
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3692328929901123,
"min": -0.014061677269637585,
"max": 2.524421215057373,
"count": 100
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1049.5701904296875,
"min": -1.701462984085083,
"max": 1528.12548828125,
"count": 100
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.5535616689018954,
"min": 1.703376503276431,
"max": 4.0851367658226065,
"count": 100
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1574.2278193235397,
"min": 206.10855689644814,
"max": 2431.3491094708443,
"count": 100
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.5535616689018954,
"min": 1.703376503276431,
"max": 4.0851367658226065,
"count": 100
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1574.2278193235397,
"min": 206.10855689644814,
"max": 2431.3491094708443,
"count": 100
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.0143986500511528,
"min": 0.0143986500511528,
"max": 0.020311779828361978,
"count": 100
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0143986500511528,
"min": 0.0143986500511528,
"max": 0.040623559656723957,
"count": 100
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.03861833775416017,
"min": 0.02063704090192914,
"max": 0.05600922778248787,
"count": 100
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.03861833775416017,
"min": 0.02063704090192914,
"max": 0.1108457275107503,
"count": 100
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.897595103400031e-07,
"min": 4.897595103400031e-07,
"max": 9.917852082148e-05,
"count": 100
},
"Huggy.Policy.LearningRate.sum": {
"value": 4.897595103400031e-07,
"min": 4.897595103400031e-07,
"max": 0.00019093786906213995,
"count": 100
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10048965999999998,
"min": 0.10048965999999998,
"max": 0.19917852000000003,
"count": 100
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.10048965999999998,
"min": 0.10048965999999998,
"max": 0.39093786,
"count": 100
},
"Huggy.Policy.Beta.mean": {
"value": 3.4434034000000145e-05,
"min": 3.4434034000000145e-05,
"max": 0.004959008148000001,
"count": 100
},
"Huggy.Policy.Beta.sum": {
"value": 3.4434034000000145e-05,
"min": 3.4434034000000145e-05,
"max": 0.009547799214000001,
"count": 100
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1670949018",
"python_version": "3.8.8 (default, Feb 24 2021, 21:46:12) \n[GCC 7.3.0]",
"command_line_arguments": "/opt/conda/bin/mlagents-learn ./src/Huggy_train_params.yaml --env=ml-agents/trained-envs-executables/linux/Huggy/Huggy --run-id=2022-12-13_16-30-16 --results-dir=./src/runs/train --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",
"numpy_version": "1.19.2",
"end_time_seconds": "1670957557"
},
"total": 8539.890615475,
"count": 1,
"self": 0.21877988599953824,
"children": {
"run_training.setup": {
"total": 0.026600823999615386,
"count": 1,
"self": 0.026600823999615386
},
"TrainerController.start_learning": {
"total": 8539.645234765001,
"count": 1,
"self": 6.5870119023784355,
"children": {
"TrainerController._reset_env": {
"total": 2.4043807759999254,
"count": 1,
"self": 2.4043807759999254
},
"TrainerController.advance": {
"total": 8530.589898061622,
"count": 580044,
"self": 6.546588201847044,
"children": {
"env_step": {
"total": 7258.6201447018875,
"count": 580044,
"self": 6869.874197223327,
"children": {
"SubprocessEnvManager._take_step": {
"total": 384.328242823874,
"count": 580044,
"self": 18.897606058662404,
"children": {
"TorchPolicy.evaluate": {
"total": 365.4306367652116,
"count": 557304,
"self": 85.71232636062223,
"children": {
"TorchPolicy.sample_actions": {
"total": 279.7183104045894,
"count": 557304,
"self": 279.7183104045894
}
}
}
}
},
"workers": {
"total": 4.4177046546860765,
"count": 580044,
"self": 0.0,
"children": {
"worker_root": {
"total": 8528.855207097244,
"count": 580044,
"is_parallel": true,
"self": 2048.4824644449563,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0005586950001088553,
"count": 1,
"is_parallel": true,
"self": 0.00019524800018189126,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00036344699992696405,
"count": 2,
"is_parallel": true,
"self": 0.00036344699992696405
}
}
},
"UnityEnvironment.step": {
"total": 0.024324938000063412,
"count": 1,
"is_parallel": true,
"self": 8.8408999999956e-05,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00029047699990769615,
"count": 1,
"is_parallel": true,
"self": 0.00029047699990769615
},
"communicator.exchange": {
"total": 0.023244918000273174,
"count": 1,
"is_parallel": true,
"self": 0.023244918000273174
},
"steps_from_proto": {
"total": 0.0007011339998825861,
"count": 1,
"is_parallel": true,
"self": 0.00011246999974900973,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005886640001335763,
"count": 2,
"is_parallel": true,
"self": 0.0005886640001335763
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 6480.372742652287,
"count": 580043,
"is_parallel": true,
"self": 36.17251831550584,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 349.6294716848397,
"count": 580043,
"is_parallel": true,
"self": 349.6294716848397
},
"communicator.exchange": {
"total": 5865.704425242987,
"count": 580043,
"is_parallel": true,
"self": 5865.704425242987
},
"steps_from_proto": {
"total": 228.86632740895493,
"count": 580043,
"is_parallel": true,
"self": 48.31774112792118,
"children": {
"_process_rank_one_or_two_observation": {
"total": 180.54858628103375,
"count": 1160086,
"is_parallel": true,
"self": 180.54858628103375
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1265.423165157887,
"count": 580044,
"self": 8.291714359180332,
"children": {
"process_trajectory": {
"total": 253.64511626268586,
"count": 580044,
"self": 252.95050172368883,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6946145389970297,
"count": 10,
"self": 0.6946145389970297
}
}
},
"_update_policy": {
"total": 1003.4863345360209,
"count": 121,
"self": 895.227036950952,
"children": {
"TorchPPOOptimizer.update": {
"total": 108.25929758506891,
"count": 12100,
"self": 108.25929758506891
}
}
}
}
}
}
},
"trainer_threads": {
"total": 6.200007192092016e-07,
"count": 1,
"self": 6.200007192092016e-07
},
"TrainerController._save_models": {
"total": 0.06394340500082762,
"count": 1,
"self": 0.0009387460013385862,
"children": {
"RLTrainer._checkpoint": {
"total": 0.06300465899948904,
"count": 1,
"self": 0.06300465899948904
}
}
}
}
}
}
}