ppo-Pyramids / run_logs /timers.json
usamabuttar's picture
First Push
909a390 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.2755347788333893,
"min": 0.24827715754508972,
"max": 1.416056513786316,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 8199.9150390625,
"min": 7432.4248046875,
"max": 42957.4921875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989924.0,
"min": 29952.0,
"max": 989924.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989924.0,
"min": 29952.0,
"max": 989924.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.6539541482925415,
"min": -0.08198705315589905,
"max": 0.6539541482925415,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 183.7611083984375,
"min": -19.840866088867188,
"max": 184.78421020507812,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.0027792686596512794,
"min": 0.0027792686596512794,
"max": 0.42529433965682983,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 0.7809745073318481,
"min": 0.7809745073318481,
"max": 100.79476165771484,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06642237757928558,
"min": 0.0635752631751866,
"max": 0.07586022215712417,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9299132861099981,
"min": 0.5011392970821665,
"max": 1.0653333288227098,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.016811673073486116,
"min": 0.0005199830136122751,
"max": 0.017390320828348023,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.23536342302880564,
"min": 0.006759779176959575,
"max": 0.26020822213225375,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.5773903313785715e-06,
"min": 7.5773903313785715e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0001060834646393,
"min": 0.0001060834646393,
"max": 0.0035090660303114,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10252576428571428,
"min": 0.10252576428571428,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4353607,
"min": 1.3886848,
"max": 2.5696886000000005,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026232385214285716,
"min": 0.00026232385214285716,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.00367253393,
"min": 0.00367253393,
"max": 0.11699189114,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.015187530778348446,
"min": 0.015187530778348446,
"max": 0.5200672745704651,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.2126254290342331,
"min": 0.2126254290342331,
"max": 3.6404707431793213,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 285.7821782178218,
"min": 281.2232142857143,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28864.0,
"min": 15984.0,
"max": 33779.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6547979995018185,
"min": -1.0000000521540642,
"max": 1.683667239032488,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 167.13459794968367,
"min": -29.994801551103592,
"max": 190.25439801067114,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6547979995018185,
"min": -1.0000000521540642,
"max": 1.683667239032488,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 167.13459794968367,
"min": -29.994801551103592,
"max": 190.25439801067114,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.04475060600910156,
"min": 0.04475060600910156,
"max": 11.373648265376687,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.5198112069192575,
"min": 4.5198112069192575,
"max": 181.978372246027,
"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": "1731079464",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1731081613"
},
"total": 2149.87468979,
"count": 1,
"self": 0.49002891600048315,
"children": {
"run_training.setup": {
"total": 0.05207508999978927,
"count": 1,
"self": 0.05207508999978927
},
"TrainerController.start_learning": {
"total": 2149.332585784,
"count": 1,
"self": 1.3008672699779709,
"children": {
"TrainerController._reset_env": {
"total": 2.592487983999945,
"count": 1,
"self": 2.592487983999945
},
"TrainerController.advance": {
"total": 2145.356232687022,
"count": 63937,
"self": 1.3561657381028454,
"children": {
"env_step": {
"total": 1474.7933231259753,
"count": 63937,
"self": 1328.5136448400667,
"children": {
"SubprocessEnvManager._take_step": {
"total": 145.4996730619282,
"count": 63937,
"self": 4.459911663851926,
"children": {
"TorchPolicy.evaluate": {
"total": 141.03976139807628,
"count": 62564,
"self": 141.03976139807628
}
}
},
"workers": {
"total": 0.7800052239804245,
"count": 63937,
"self": 0.0,
"children": {
"worker_root": {
"total": 2145.0218759470667,
"count": 63937,
"is_parallel": true,
"self": 926.5758009700621,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0021229210001365573,
"count": 1,
"is_parallel": true,
"self": 0.0006994230000145762,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001423498000121981,
"count": 8,
"is_parallel": true,
"self": 0.001423498000121981
}
}
},
"UnityEnvironment.step": {
"total": 0.10249720499996329,
"count": 1,
"is_parallel": true,
"self": 0.0006519719997868378,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004156449999754841,
"count": 1,
"is_parallel": true,
"self": 0.0004156449999754841
},
"communicator.exchange": {
"total": 0.09976565700003448,
"count": 1,
"is_parallel": true,
"self": 0.09976565700003448
},
"steps_from_proto": {
"total": 0.0016639310001664853,
"count": 1,
"is_parallel": true,
"self": 0.00035573700029090105,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013081939998755843,
"count": 8,
"is_parallel": true,
"self": 0.0013081939998755843
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1218.4460749770046,
"count": 63936,
"is_parallel": true,
"self": 32.73257503295076,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.081975038047403,
"count": 63936,
"is_parallel": true,
"self": 23.081975038047403
},
"communicator.exchange": {
"total": 1066.3283353119746,
"count": 63936,
"is_parallel": true,
"self": 1066.3283353119746
},
"steps_from_proto": {
"total": 96.30318959403189,
"count": 63936,
"is_parallel": true,
"self": 19.566949659889815,
"children": {
"_process_rank_one_or_two_observation": {
"total": 76.73623993414208,
"count": 511488,
"is_parallel": true,
"self": 76.73623993414208
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 669.2067438229435,
"count": 63937,
"self": 2.4583449569793174,
"children": {
"process_trajectory": {
"total": 128.29734714196275,
"count": 63937,
"self": 128.09948033496312,
"children": {
"RLTrainer._checkpoint": {
"total": 0.19786680699962744,
"count": 2,
"self": 0.19786680699962744
}
}
},
"_update_policy": {
"total": 538.4510517240014,
"count": 456,
"self": 301.5205892630436,
"children": {
"TorchPPOOptimizer.update": {
"total": 236.93046246095787,
"count": 22824,
"self": 236.93046246095787
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0650001058820635e-06,
"count": 1,
"self": 1.0650001058820635e-06
},
"TrainerController._save_models": {
"total": 0.08299677800005156,
"count": 1,
"self": 0.001432797999768809,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08156398000028275,
"count": 1,
"self": 0.08156398000028275
}
}
}
}
}
}
}