ppo-Pyramid / run_logs /timers.json
joigalcar's picture
First Push
7921d61 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.2773354649543762,
"min": 0.2773354649543762,
"max": 1.4073975086212158,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 8373.3125,
"min": 8373.3125,
"max": 42694.8125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989939.0,
"min": 29933.0,
"max": 989939.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989939.0,
"min": 29933.0,
"max": 989939.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.6236056685447693,
"min": -0.12565401196479797,
"max": 0.6605077385902405,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 178.97482299804688,
"min": -29.780000686645508,
"max": 192.86825561523438,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.0008548194891773164,
"min": -0.0036664961371570826,
"max": 0.5945931673049927,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -0.24533319473266602,
"min": -0.9826209545135498,
"max": 140.9185791015625,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06783710452096439,
"min": 0.0661386817954112,
"max": 0.07332952766557269,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0175565678144658,
"min": 0.510506389013976,
"max": 1.0450892165924115,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015623487017096137,
"min": 0.0006422254618609472,
"max": 0.017076887696194244,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.23435230525644205,
"min": 0.007706705542331367,
"max": 0.2390764277467194,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.500597499833337e-06,
"min": 7.500597499833337e-06,
"max": 0.0002952337301601857,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00011250896249750005,
"min": 0.00011250896249750005,
"max": 0.0035080169306611,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10250016666666668,
"min": 0.10250016666666668,
"max": 0.19841124285714287,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5375025000000002,
"min": 1.3888787,
"max": 2.5693388999999995,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025976665000000004,
"min": 0.00025976665000000004,
"max": 0.009841283161428571,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003896499750000001,
"min": 0.003896499750000001,
"max": 0.11695695611,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.00876538921147585,
"min": 0.00876538921147585,
"max": 0.50517338514328,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1314808428287506,
"min": 0.12519557774066925,
"max": 3.5362138748168945,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 300.41,
"min": 288.6818181818182,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30041.0,
"min": 16604.0,
"max": 32393.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6595859810709954,
"min": -0.9999806972280625,
"max": 1.6685835131827522,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 165.95859810709953,
"min": -31.998801663517952,
"max": 180.64979817718267,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6595859810709954,
"min": -0.9999806972280625,
"max": 1.6685835131827522,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 165.95859810709953,
"min": -31.998801663517952,
"max": 180.64979817718267,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.0270965118627646,
"min": 0.0270965118627646,
"max": 10.139183421345319,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.70965118627646,
"min": 2.6888521583750844,
"max": 172.3661181628704,
"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": "1737930164",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "2.5.1+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1737932378"
},
"total": 2213.847520931,
"count": 1,
"self": 0.47616378199927567,
"children": {
"run_training.setup": {
"total": 0.028838968000854948,
"count": 1,
"self": 0.028838968000854948
},
"TrainerController.start_learning": {
"total": 2213.342518181,
"count": 1,
"self": 1.2272421029210818,
"children": {
"TrainerController._reset_env": {
"total": 1.9030625359991973,
"count": 1,
"self": 1.9030625359991973
},
"TrainerController.advance": {
"total": 2210.130469330079,
"count": 64218,
"self": 1.2752446611084451,
"children": {
"env_step": {
"total": 1542.9697438570347,
"count": 64218,
"self": 1395.9114250848597,
"children": {
"SubprocessEnvManager._take_step": {
"total": 146.3454012092443,
"count": 64218,
"self": 4.467500006196133,
"children": {
"TorchPolicy.evaluate": {
"total": 141.87790120304817,
"count": 62554,
"self": 141.87790120304817
}
}
},
"workers": {
"total": 0.7129175629306701,
"count": 64218,
"self": 0.0,
"children": {
"worker_root": {
"total": 2208.4807133307913,
"count": 64218,
"is_parallel": true,
"self": 921.6180422255402,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0020442580007511424,
"count": 1,
"is_parallel": true,
"self": 0.0006695229985780315,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013747350021731108,
"count": 8,
"is_parallel": true,
"self": 0.0013747350021731108
}
}
},
"UnityEnvironment.step": {
"total": 0.04942460799975379,
"count": 1,
"is_parallel": true,
"self": 0.0005216089994064532,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004713649996119784,
"count": 1,
"is_parallel": true,
"self": 0.0004713649996119784
},
"communicator.exchange": {
"total": 0.046747952001169324,
"count": 1,
"is_parallel": true,
"self": 0.046747952001169324
},
"steps_from_proto": {
"total": 0.0016836819995660335,
"count": 1,
"is_parallel": true,
"self": 0.0003738409977813717,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013098410017846618,
"count": 8,
"is_parallel": true,
"self": 0.0013098410017846618
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1286.8626711052511,
"count": 64217,
"is_parallel": true,
"self": 30.784486242657294,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.0049097328847,
"count": 64217,
"is_parallel": true,
"self": 23.0049097328847
},
"communicator.exchange": {
"total": 1138.3662073478135,
"count": 64217,
"is_parallel": true,
"self": 1138.3662073478135
},
"steps_from_proto": {
"total": 94.7070677818956,
"count": 64217,
"is_parallel": true,
"self": 18.9804970262976,
"children": {
"_process_rank_one_or_two_observation": {
"total": 75.726570755598,
"count": 513736,
"is_parallel": true,
"self": 75.726570755598
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 665.8854808119358,
"count": 64218,
"self": 2.4143455310422723,
"children": {
"process_trajectory": {
"total": 124.82917850788544,
"count": 64218,
"self": 124.6186886708856,
"children": {
"RLTrainer._checkpoint": {
"total": 0.21048983699984092,
"count": 2,
"self": 0.21048983699984092
}
}
},
"_update_policy": {
"total": 538.6419567730081,
"count": 454,
"self": 297.0462033972435,
"children": {
"TorchPPOOptimizer.update": {
"total": 241.59575337576462,
"count": 22764,
"self": 241.59575337576462
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.420010999543592e-07,
"count": 1,
"self": 8.420010999543592e-07
},
"TrainerController._save_models": {
"total": 0.08174336999945808,
"count": 1,
"self": 0.0012653909980144817,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0804779790014436,
"count": 1,
"self": 0.0804779790014436
}
}
}
}
}
}
}