ppo-Pyramids / run_logs /timers.json
opria123's picture
train
7711aa1 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.026697808876633644,
"min": 0.023501353338360786,
"max": 1.4180653095245361,
"count": 100
},
"Pyramids.Policy.Entropy.sum": {
"value": 791.1094970703125,
"min": 703.9125366210938,
"max": 43018.4296875,
"count": 100
},
"Pyramids.Step.mean": {
"value": 2999885.0,
"min": 29952.0,
"max": 2999885.0,
"count": 100
},
"Pyramids.Step.sum": {
"value": 2999885.0,
"min": 29952.0,
"max": 2999885.0,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.08667800575494766,
"min": -0.12488041818141937,
"max": 0.07857930660247803,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": -20.80272102355957,
"min": -30.22106170654297,
"max": 18.623294830322266,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.4166210889816284,
"min": 0.2931205630302429,
"max": 0.8160367012023926,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 99.98905944824219,
"min": 71.2282943725586,
"max": 193.40069580078125,
"count": 100
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06743713267570159,
"min": 0.06441511953725997,
"max": 0.0745779834457814,
"count": 100
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9441198574598223,
"min": 0.47610507552524034,
"max": 1.0848496769875626,
"count": 100
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.0006816408889769799,
"min": 0.00011742210585875899,
"max": 0.017913300777857737,
"count": 100
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.009542972445677719,
"min": 0.0016439094820226258,
"max": 0.12539310544500415,
"count": 100
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.417206670488096e-06,
"min": 1.417206670488096e-06,
"max": 0.00029838354339596195,
"count": 100
},
"Pyramids.Policy.LearningRate.sum": {
"value": 1.9840893386833343e-05,
"min": 1.9840893386833343e-05,
"max": 0.004027357857547434,
"count": 100
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10047236904761904,
"min": 0.10047236904761904,
"max": 0.19946118095238097,
"count": 100
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4066131666666666,
"min": 1.3897045333333333,
"max": 2.842452566666667,
"count": 100
},
"Pyramids.Policy.Beta.mean": {
"value": 5.7189667857142884e-05,
"min": 5.7189667857142884e-05,
"max": 0.009946171977142856,
"count": 100
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0008006553500000004,
"min": 0.0008006553500000004,
"max": 0.13426101141,
"count": 100
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.41239994764328003,
"min": 0.2975112497806549,
"max": 0.8626972436904907,
"count": 100
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 5.773599147796631,
"min": 2.56459903717041,
"max": 6.230391502380371,
"count": 100
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 991.0344827586207,
"min": 898.1714285714286,
"max": 999.0,
"count": 100
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28740.0,
"min": 15984.0,
"max": 33462.0,
"count": 100
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": -0.9253400517006715,
"min": -1.0000000521540642,
"max": -0.49873719066381456,
"count": 100
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": -27.760201551020145,
"min": -32.000001668930054,
"max": -16.000000834465027,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": -0.9253400517006715,
"min": -1.0000000521540642,
"max": -0.49873719066381456,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": -27.760201551020145,
"min": -32.000001668930054,
"max": -16.000000834465027,
"count": 100
},
"Pyramids.Policy.RndReward.mean": {
"value": 4.0757664816143615,
"min": 2.650617757868586,
"max": 17.517017476260662,
"count": 100
},
"Pyramids.Policy.RndReward.sum": {
"value": 122.27299444843084,
"min": 84.95376480743289,
"max": 280.2722796201706,
"count": 100
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1744938273",
"python_version": "3.10.12 (main, Feb 4 2025, 14:57:36) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1744941733"
},
"total": 3460.453336695,
"count": 1,
"self": 0.42342376000033255,
"children": {
"run_training.setup": {
"total": 0.0413516829994478,
"count": 1,
"self": 0.0413516829994478
},
"TrainerController.start_learning": {
"total": 3459.988561252,
"count": 1,
"self": 2.235014651887468,
"children": {
"TrainerController._reset_env": {
"total": 5.148095538999769,
"count": 1,
"self": 5.148095538999769
},
"TrainerController.advance": {
"total": 3452.4606732711127,
"count": 189411,
"self": 1.9776961202014718,
"children": {
"env_step": {
"total": 2603.809506384805,
"count": 189411,
"self": 2469.9244019448415,
"children": {
"SubprocessEnvManager._take_step": {
"total": 132.46685628473188,
"count": 189411,
"self": 5.695118515698596,
"children": {
"TorchPolicy.evaluate": {
"total": 126.77173776903328,
"count": 187549,
"self": 126.77173776903328
}
}
},
"workers": {
"total": 1.4182481552315949,
"count": 189411,
"self": 0.0,
"children": {
"worker_root": {
"total": 3453.6376040860378,
"count": 189411,
"is_parallel": true,
"self": 1135.133600393081,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011791739998443518,
"count": 1,
"is_parallel": true,
"self": 0.00034231700010423083,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000836856999740121,
"count": 8,
"is_parallel": true,
"self": 0.000836856999740121
}
}
},
"UnityEnvironment.step": {
"total": 0.035390193999774056,
"count": 1,
"is_parallel": true,
"self": 0.00016355000025214395,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00017133500023192028,
"count": 1,
"is_parallel": true,
"self": 0.00017133500023192028
},
"communicator.exchange": {
"total": 0.034527056999650085,
"count": 1,
"is_parallel": true,
"self": 0.034527056999650085
},
"steps_from_proto": {
"total": 0.000528251999639906,
"count": 1,
"is_parallel": true,
"self": 0.00013423200107354205,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00039401999856636394,
"count": 8,
"is_parallel": true,
"self": 0.00039401999856636394
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 2318.5040036929568,
"count": 189410,
"is_parallel": true,
"self": 24.308748942910825,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 21.538117956945825,
"count": 189410,
"is_parallel": true,
"self": 21.538117956945825
},
"communicator.exchange": {
"total": 2201.9324355412,
"count": 189410,
"is_parallel": true,
"self": 2201.9324355412
},
"steps_from_proto": {
"total": 70.72470125190011,
"count": 189410,
"is_parallel": true,
"self": 17.529140876373276,
"children": {
"_process_rank_one_or_two_observation": {
"total": 53.19556037552684,
"count": 1515280,
"is_parallel": true,
"self": 53.19556037552684
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 846.6734707661062,
"count": 189411,
"self": 4.618809433937713,
"children": {
"process_trajectory": {
"total": 174.12017955114243,
"count": 189411,
"self": 173.45124205714365,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6689374939987829,
"count": 6,
"self": 0.6689374939987829
}
}
},
"_update_policy": {
"total": 667.9344817810261,
"count": 1386,
"self": 375.3033519739647,
"children": {
"TorchPPOOptimizer.update": {
"total": 292.63112980706137,
"count": 68142,
"self": 292.63112980706137
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.220005500130355e-07,
"count": 1,
"self": 7.220005500130355e-07
},
"TrainerController._save_models": {
"total": 0.14477706799971202,
"count": 1,
"self": 0.03152231999956712,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1132547480001449,
"count": 1,
"self": 0.1132547480001449
}
}
}
}
}
}
}