ppo-Huggy-2 / run_logs /timers.json
omiro's picture
Huggy
1b9fc6c
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4014666080474854,
"min": 1.4014666080474854,
"max": 1.4258346557617188,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71452.375,
"min": 68751.265625,
"max": 75817.1171875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 81.34364820846906,
"min": 75.04255319148936,
"max": 393.84251968503935,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49945.0,
"min": 49184.0,
"max": 50496.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999836.0,
"min": 49471.0,
"max": 1999836.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999836.0,
"min": 49471.0,
"max": 1999836.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4776949882507324,
"min": -0.049760229885578156,
"max": 2.4776949882507324,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1521.3046875,
"min": -6.26978874206543,
"max": 1592.93115234375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8911652920300486,
"min": 1.8448395125922703,
"max": 3.9905613230511467,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2389.17548930645,
"min": 232.44977858662605,
"max": 2517.9809032082558,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8911652920300486,
"min": 1.8448395125922703,
"max": 3.9905613230511467,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2389.17548930645,
"min": 232.44977858662605,
"max": 2517.9809032082558,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016692240014648026,
"min": 0.01393320200246914,
"max": 0.019088289291499274,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.050076720043944076,
"min": 0.02786640400493828,
"max": 0.05726486787449782,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06243273512356812,
"min": 0.022808060950289172,
"max": 0.06243273512356812,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18729820537070435,
"min": 0.045616121900578344,
"max": 0.18729820537070435,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.666048778016662e-06,
"min": 3.666048778016662e-06,
"max": 0.0002953404765531749,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0998146334049985e-05,
"min": 1.0998146334049985e-05,
"max": 0.0008440518186494,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10122198333333333,
"min": 0.10122198333333333,
"max": 0.198446825,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30366595,
"min": 0.20757050000000005,
"max": 0.5813506000000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.097696833333328e-05,
"min": 7.097696833333328e-05,
"max": 0.004922496567500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021293090499999986,
"min": 0.00021293090499999986,
"max": 0.014069394939999999,
"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": "1695564565",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics --resume",
"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": "1695567071"
},
"total": 2506.211791291,
"count": 1,
"self": 0.7015950219993101,
"children": {
"run_training.setup": {
"total": 0.03955702899997959,
"count": 1,
"self": 0.03955702899997959
},
"TrainerController.start_learning": {
"total": 2505.4706392400003,
"count": 1,
"self": 4.556607315098518,
"children": {
"TrainerController._reset_env": {
"total": 5.121893449999902,
"count": 1,
"self": 5.121893449999902
},
"TrainerController.advance": {
"total": 2495.602893055902,
"count": 232916,
"self": 4.595960764857864,
"children": {
"env_step": {
"total": 1932.8325782580184,
"count": 232916,
"self": 1629.1233160680372,
"children": {
"SubprocessEnvManager._take_step": {
"total": 300.6411938470387,
"count": 232916,
"self": 17.324263622937224,
"children": {
"TorchPolicy.evaluate": {
"total": 283.3169302241015,
"count": 222982,
"self": 283.3169302241015
}
}
},
"workers": {
"total": 3.0680683429425244,
"count": 232916,
"self": 0.0,
"children": {
"worker_root": {
"total": 2497.6845285060153,
"count": 232916,
"is_parallel": true,
"self": 1168.04255654897,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0007669200000464116,
"count": 1,
"is_parallel": true,
"self": 0.00021646000004693633,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005504599999994753,
"count": 2,
"is_parallel": true,
"self": 0.0005504599999994753
}
}
},
"UnityEnvironment.step": {
"total": 0.045593012000153976,
"count": 1,
"is_parallel": true,
"self": 0.00030102700020506745,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00024474600013491,
"count": 1,
"is_parallel": true,
"self": 0.00024474600013491
},
"communicator.exchange": {
"total": 0.044304011999884096,
"count": 1,
"is_parallel": true,
"self": 0.044304011999884096
},
"steps_from_proto": {
"total": 0.0007432269999299024,
"count": 1,
"is_parallel": true,
"self": 0.00021429200000966375,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005289349999202386,
"count": 2,
"is_parallel": true,
"self": 0.0005289349999202386
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1329.6419719570454,
"count": 232915,
"is_parallel": true,
"self": 39.4819519447517,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 85.01191203398616,
"count": 232915,
"is_parallel": true,
"self": 85.01191203398616
},
"communicator.exchange": {
"total": 1102.6366336402507,
"count": 232915,
"is_parallel": true,
"self": 1102.6366336402507
},
"steps_from_proto": {
"total": 102.51147433805681,
"count": 232915,
"is_parallel": true,
"self": 38.29673927306135,
"children": {
"_process_rank_one_or_two_observation": {
"total": 64.21473506499547,
"count": 465830,
"is_parallel": true,
"self": 64.21473506499547
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 558.1743540330256,
"count": 232916,
"self": 6.962386167012028,
"children": {
"process_trajectory": {
"total": 144.52368637801465,
"count": 232916,
"self": 143.1740970890139,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3495892890007326,
"count": 10,
"self": 1.3495892890007326
}
}
},
"_update_policy": {
"total": 406.6882814879989,
"count": 97,
"self": 346.4525271830007,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.23575430499818,
"count": 2910,
"self": 60.23575430499818
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4629999895987567e-06,
"count": 1,
"self": 1.4629999895987567e-06
},
"TrainerController._save_models": {
"total": 0.18924395600015487,
"count": 1,
"self": 0.004947881000589405,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18429607499956546,
"count": 1,
"self": 0.18429607499956546
}
}
}
}
}
}
}