ppo-Pyramids / run_logs /timers.json
elliemci's picture
First training of Pyramids
e8ab93d verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.1392391473054886,
"min": 0.13144154846668243,
"max": 1.348419189453125,
"count": 100
},
"Pyramids.Policy.Entropy.sum": {
"value": 4186.0859375,
"min": 3926.421875,
"max": 40905.64453125,
"count": 100
},
"Pyramids.Step.mean": {
"value": 2999878.0,
"min": 29952.0,
"max": 2999878.0,
"count": 100
},
"Pyramids.Step.sum": {
"value": 2999878.0,
"min": 29952.0,
"max": 2999878.0,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.8312862515449524,
"min": -0.09473264962434769,
"max": 0.9086430072784424,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 249.38587951660156,
"min": -22.92530059814453,
"max": 281.703369140625,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.033841684460639954,
"min": -0.038781892508268356,
"max": 0.5027545094490051,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 10.152505874633789,
"min": -10.936493873596191,
"max": 119.15282440185547,
"count": 100
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06914138440784595,
"min": 0.06483830381434277,
"max": 0.07556318708798028,
"count": 100
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0371207661176893,
"min": 0.474166578898573,
"max": 1.1065460388153772,
"count": 100
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015655294647234877,
"min": 0.00023124339060860875,
"max": 0.019066683018177998,
"count": 100
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.23482941970852314,
"min": 0.003006164077911914,
"max": 0.24095477683780092,
"count": 100
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.5143394952533336e-06,
"min": 1.5143394952533336e-06,
"max": 0.00029838354339596195,
"count": 100
},
"Pyramids.Policy.LearningRate.sum": {
"value": 2.2715092428800004e-05,
"min": 2.2715092428800004e-05,
"max": 0.003969243876918733,
"count": 100
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10050474666666666,
"min": 0.10050474666666666,
"max": 0.19946118095238097,
"count": 100
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5075712,
"min": 1.3962282666666668,
"max": 2.7526238666666667,
"count": 100
},
"Pyramids.Policy.Beta.mean": {
"value": 6.0424192e-05,
"min": 6.0424192e-05,
"max": 0.009946171977142856,
"count": 100
},
"Pyramids.Policy.Beta.sum": {
"value": 0.00090636288,
"min": 0.00090636288,
"max": 0.13231581854000002,
"count": 100
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.00956425629556179,
"min": 0.008899449370801449,
"max": 0.7356981635093689,
"count": 100
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1434638500213623,
"min": 0.12459228932857513,
"max": 5.1498870849609375,
"count": 100
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 230.13636363636363,
"min": 194.41935483870967,
"max": 999.0,
"count": 100
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30378.0,
"min": 15984.0,
"max": 33364.0,
"count": 100
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7405894609322226,
"min": -1.0000000521540642,
"max": 1.8018039060768738,
"count": 100
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 231.4983983039856,
"min": -31.996801674365997,
"max": 275.6759976297617,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7405894609322226,
"min": -1.0000000521540642,
"max": 1.8018039060768738,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 231.4983983039856,
"min": -31.996801674365997,
"max": 275.6759976297617,
"count": 100
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.022765637689648212,
"min": 0.018957090894391095,
"max": 15.026027102023363,
"count": 100
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.027829812723212,
"min": 2.611550264802645,
"max": 240.4164336323738,
"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": "1759539206",
"python_version": "3.10.12 (main, Aug 15 2025, 14:32:43) [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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1759546896"
},
"total": 7689.933570825999,
"count": 1,
"self": 1.0605829899996024,
"children": {
"run_training.setup": {
"total": 0.035859583998899325,
"count": 1,
"self": 0.035859583998899325
},
"TrainerController.start_learning": {
"total": 7688.837128252,
"count": 1,
"self": 4.442821187914888,
"children": {
"TrainerController._reset_env": {
"total": 5.3456897610012675,
"count": 1,
"self": 5.3456897610012675
},
"TrainerController.advance": {
"total": 7678.865367545084,
"count": 195558,
"self": 4.483650827329257,
"children": {
"env_step": {
"total": 5596.575091723296,
"count": 195558,
"self": 5134.483039991339,
"children": {
"SubprocessEnvManager._take_step": {
"total": 459.37762890377417,
"count": 195558,
"self": 14.581460051598697,
"children": {
"TorchPolicy.evaluate": {
"total": 444.79616885217547,
"count": 187556,
"self": 444.79616885217547
}
}
},
"workers": {
"total": 2.71442282818316,
"count": 195558,
"self": 0.0,
"children": {
"worker_root": {
"total": 7664.609600366375,
"count": 195558,
"is_parallel": true,
"self": 2908.602627748016,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001942161999977543,
"count": 1,
"is_parallel": true,
"self": 0.0006128590030129999,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013293029969645431,
"count": 8,
"is_parallel": true,
"self": 0.0013293029969645431
}
}
},
"UnityEnvironment.step": {
"total": 0.1386621269994066,
"count": 1,
"is_parallel": true,
"self": 0.000528401000337908,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004412689995660912,
"count": 1,
"is_parallel": true,
"self": 0.0004412689995660912
},
"communicator.exchange": {
"total": 0.13357365899901197,
"count": 1,
"is_parallel": true,
"self": 0.13357365899901197
},
"steps_from_proto": {
"total": 0.004118798000490642,
"count": 1,
"is_parallel": true,
"self": 0.00038331799987645354,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0037354800006141886,
"count": 8,
"is_parallel": true,
"self": 0.0037354800006141886
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 4756.006972618359,
"count": 195557,
"is_parallel": true,
"self": 103.0249369156736,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 71.573377633762,
"count": 195557,
"is_parallel": true,
"self": 71.573377633762
},
"communicator.exchange": {
"total": 4230.095343374864,
"count": 195557,
"is_parallel": true,
"self": 4230.095343374864
},
"steps_from_proto": {
"total": 351.31331469405995,
"count": 195557,
"is_parallel": true,
"self": 75.9351448016605,
"children": {
"_process_rank_one_or_two_observation": {
"total": 275.37816989239946,
"count": 1564456,
"is_parallel": true,
"self": 275.37816989239946
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 2077.8066249944586,
"count": 195558,
"self": 8.835137466157903,
"children": {
"process_trajectory": {
"total": 418.0839418593114,
"count": 195558,
"self": 417.21445004331144,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8694918159999361,
"count": 6,
"self": 0.8694918159999361
}
}
},
"_update_policy": {
"total": 1650.8875456689893,
"count": 1400,
"self": 925.8207568159578,
"children": {
"TorchPPOOptimizer.update": {
"total": 725.0667888530315,
"count": 68382,
"self": 725.0667888530315
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3989993021823466e-06,
"count": 1,
"self": 1.3989993021823466e-06
},
"TrainerController._save_models": {
"total": 0.18324835900057224,
"count": 1,
"self": 0.014127578997431556,
"children": {
"RLTrainer._checkpoint": {
"total": 0.16912078000314068,
"count": 1,
"self": 0.16912078000314068
}
}
}
}
}
}
}