ppo-Pyramid / run_logs /timers.json
ethan-lam's picture
First Push
d8cbeae verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.39514854550361633,
"min": 0.38591161370277405,
"max": 1.4020886421203613,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 11835.4892578125,
"min": 11645.2685546875,
"max": 42533.76171875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989959.0,
"min": 29952.0,
"max": 989959.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989959.0,
"min": 29952.0,
"max": 989959.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.41675296425819397,
"min": -0.12393856793642044,
"max": 0.5223228931427002,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 110.02278137207031,
"min": -29.745256423950195,
"max": 146.2504119873047,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.011569817550480366,
"min": -0.026645349338650703,
"max": 0.36610883474349976,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -3.054431915283203,
"min": -7.167598724365234,
"max": 86.76779174804688,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06827704559844341,
"min": 0.06579154781981389,
"max": 0.0731155229565815,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9558786383782077,
"min": 0.49046836578522696,
"max": 1.0514411457463888,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015066549895919537,
"min": 0.0002874296038484316,
"max": 0.01532879044998778,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.21093169854287352,
"min": 0.0037365848500296108,
"max": 0.2299318567498167,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.597661753192853e-06,
"min": 7.597661753192853e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010636726454469994,
"min": 0.00010636726454469994,
"max": 0.0036092832969056,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10253252142857143,
"min": 0.10253252142857143,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4354553,
"min": 1.3886848,
"max": 2.5690832000000006,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002629988907142856,
"min": 0.0002629988907142856,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036819844699999982,
"min": 0.0036819844699999982,
"max": 0.12031913056,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.01025515515357256,
"min": 0.01025515515357256,
"max": 0.46993961930274963,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.14357216656208038,
"min": 0.14357216656208038,
"max": 3.2895772457122803,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 402.88,
"min": 354.0,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30216.0,
"min": 15984.0,
"max": 32875.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.457657866474045,
"min": -1.0000000521540642,
"max": 1.5991627755899762,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 110.78199785202742,
"min": -29.996001556515694,
"max": 137.52799870073795,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.457657866474045,
"min": -1.0000000521540642,
"max": 1.5991627755899762,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 110.78199785202742,
"min": -29.996001556515694,
"max": 137.52799870073795,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.043237536223865676,
"min": 0.04128636280040874,
"max": 9.16056789085269,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.2860527530137915,
"min": 3.071183182648383,
"max": 146.56908625364304,
"count": 33
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1712550329",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1712552525"
},
"total": 2196.107547089,
"count": 1,
"self": 0.4960180389998641,
"children": {
"run_training.setup": {
"total": 0.05281163899985586,
"count": 1,
"self": 0.05281163899985586
},
"TrainerController.start_learning": {
"total": 2195.558717411,
"count": 1,
"self": 1.4247566709641433,
"children": {
"TrainerController._reset_env": {
"total": 2.1933096790000945,
"count": 1,
"self": 2.1933096790000945
},
"TrainerController.advance": {
"total": 2191.851127950036,
"count": 63689,
"self": 1.3891666360755153,
"children": {
"env_step": {
"total": 1564.0222311989096,
"count": 63689,
"self": 1433.633022290895,
"children": {
"SubprocessEnvManager._take_step": {
"total": 129.58135657600428,
"count": 63689,
"self": 4.648342784930037,
"children": {
"TorchPolicy.evaluate": {
"total": 124.93301379107425,
"count": 62547,
"self": 124.93301379107425
}
}
},
"workers": {
"total": 0.8078523320102704,
"count": 63689,
"self": 0.0,
"children": {
"worker_root": {
"total": 2190.553956606039,
"count": 63689,
"is_parallel": true,
"self": 875.3343323429444,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0020666319999236293,
"count": 1,
"is_parallel": true,
"self": 0.0006282679996729712,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014383640002506581,
"count": 8,
"is_parallel": true,
"self": 0.0014383640002506581
}
}
},
"UnityEnvironment.step": {
"total": 0.04665200099998401,
"count": 1,
"is_parallel": true,
"self": 0.0006262930000957567,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004580959998747858,
"count": 1,
"is_parallel": true,
"self": 0.0004580959998747858
},
"communicator.exchange": {
"total": 0.043885730000056355,
"count": 1,
"is_parallel": true,
"self": 0.043885730000056355
},
"steps_from_proto": {
"total": 0.0016818819999571133,
"count": 1,
"is_parallel": true,
"self": 0.00035757000023295404,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013243119997241593,
"count": 8,
"is_parallel": true,
"self": 0.0013243119997241593
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1315.2196242630944,
"count": 63688,
"is_parallel": true,
"self": 34.2870851792286,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.12452676495218,
"count": 63688,
"is_parallel": true,
"self": 24.12452676495218
},
"communicator.exchange": {
"total": 1157.729623620984,
"count": 63688,
"is_parallel": true,
"self": 1157.729623620984
},
"steps_from_proto": {
"total": 99.07838869792954,
"count": 63688,
"is_parallel": true,
"self": 19.953452029825485,
"children": {
"_process_rank_one_or_two_observation": {
"total": 79.12493666810406,
"count": 509504,
"is_parallel": true,
"self": 79.12493666810406
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 626.4397301150507,
"count": 63689,
"self": 2.6233026290210546,
"children": {
"process_trajectory": {
"total": 125.33210488502618,
"count": 63689,
"self": 125.12782780402631,
"children": {
"RLTrainer._checkpoint": {
"total": 0.20427708099987285,
"count": 2,
"self": 0.20427708099987285
}
}
},
"_update_policy": {
"total": 498.48432260100344,
"count": 454,
"self": 290.9653606320685,
"children": {
"TorchPPOOptimizer.update": {
"total": 207.51896196893495,
"count": 22764,
"self": 207.51896196893495
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.99999883788405e-07,
"count": 1,
"self": 9.99999883788405e-07
},
"TrainerController._save_models": {
"total": 0.08952211099995111,
"count": 1,
"self": 0.0014832949996161915,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08803881600033492,
"count": 1,
"self": 0.08803881600033492
}
}
}
}
}
}
}