ppo-Pyramids / run_logs /timers.json
akoshel's picture
First Push
eb07114
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.43299514055252075,
"min": 0.431625634431839,
"max": 1.4150054454803467,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 13079.9169921875,
"min": 13073.0771484375,
"max": 42925.60546875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989983.0,
"min": 29939.0,
"max": 989983.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989983.0,
"min": 29939.0,
"max": 989983.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5747219920158386,
"min": -0.09247121214866638,
"max": 0.6153026223182678,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 160.92214965820312,
"min": -22.193090438842773,
"max": 172.90003967285156,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.012251561507582664,
"min": -0.05793634057044983,
"max": 0.26780444383621216,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 3.4304373264312744,
"min": -15.1793212890625,
"max": 63.46965408325195,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07055523776713725,
"min": 0.06420797747328737,
"max": 0.07245905621610556,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9877733287399214,
"min": 0.48797162086870144,
"max": 1.0454738520396252,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015968882682846883,
"min": 0.00020262078701604718,
"max": 0.01794083535441175,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.22356435755985637,
"min": 0.002431449444192566,
"max": 0.2511716949617645,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.343068980914288e-06,
"min": 7.343068980914288e-06,
"max": 0.00029523347301741424,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010280296573280003,
"min": 0.00010280296573280003,
"max": 0.0032549087150305,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10244765714285713,
"min": 0.10244765714285713,
"max": 0.19841115714285712,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4342671999999999,
"min": 1.3888781,
"max": 2.4003365000000003,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025452094857142865,
"min": 0.00025452094857142865,
"max": 0.009841274598571427,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003563293280000001,
"min": 0.003563293280000001,
"max": 0.10851845305,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.01158502884209156,
"min": 0.011480961926281452,
"max": 0.37756672501564026,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.16219040751457214,
"min": 0.16073346138000488,
"max": 2.6429669857025146,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 341.30337078651684,
"min": 306.21276595744683,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30376.0,
"min": 16610.0,
"max": 32909.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6347533136606216,
"min": -0.9999500522390008,
"max": 1.6958279428623055,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 147.12779822945595,
"min": -31.998401671648026,
"max": 157.71199868619442,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6347533136606216,
"min": -0.9999500522390008,
"max": 1.6958279428623055,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 147.12779822945595,
"min": -31.998401671648026,
"max": 157.71199868619442,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.04156679431875495,
"min": 0.03771317993185573,
"max": 7.640035626642844,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.7410114886879455,
"min": 3.507325733662583,
"max": 129.88060565292835,
"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": "1676964336",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1676966584"
},
"total": 2248.033456663,
"count": 1,
"self": 0.5909293959998649,
"children": {
"run_training.setup": {
"total": 0.17199249699996244,
"count": 1,
"self": 0.17199249699996244
},
"TrainerController.start_learning": {
"total": 2247.2705347700003,
"count": 1,
"self": 1.300721454012546,
"children": {
"TrainerController._reset_env": {
"total": 10.011437704999992,
"count": 1,
"self": 10.011437704999992
},
"TrainerController.advance": {
"total": 2235.874354963988,
"count": 63758,
"self": 1.4307974500284217,
"children": {
"env_step": {
"total": 1500.850537270972,
"count": 63758,
"self": 1389.4086489530148,
"children": {
"SubprocessEnvManager._take_step": {
"total": 110.61930640699421,
"count": 63758,
"self": 4.507230859978392,
"children": {
"TorchPolicy.evaluate": {
"total": 106.11207554701582,
"count": 62577,
"self": 35.51953688800205,
"children": {
"TorchPolicy.sample_actions": {
"total": 70.59253865901377,
"count": 62577,
"self": 70.59253865901377
}
}
}
}
},
"workers": {
"total": 0.8225819109629242,
"count": 63758,
"self": 0.0,
"children": {
"worker_root": {
"total": 2242.392339225958,
"count": 63758,
"is_parallel": true,
"self": 966.687245053994,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.010062871999991785,
"count": 1,
"is_parallel": true,
"self": 0.004017834999956449,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.006045037000035336,
"count": 8,
"is_parallel": true,
"self": 0.006045037000035336
}
}
},
"UnityEnvironment.step": {
"total": 0.04596286599996802,
"count": 1,
"is_parallel": true,
"self": 0.0005265929999609398,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004689830000188522,
"count": 1,
"is_parallel": true,
"self": 0.0004689830000188522
},
"communicator.exchange": {
"total": 0.04336534999998776,
"count": 1,
"is_parallel": true,
"self": 0.04336534999998776
},
"steps_from_proto": {
"total": 0.001601940000000468,
"count": 1,
"is_parallel": true,
"self": 0.00040490199995701914,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011970380000434488,
"count": 8,
"is_parallel": true,
"self": 0.0011970380000434488
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1275.705094171964,
"count": 63757,
"is_parallel": true,
"self": 31.39147569697934,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.484104850010624,
"count": 63757,
"is_parallel": true,
"self": 22.484104850010624
},
"communicator.exchange": {
"total": 1129.5745604429899,
"count": 63757,
"is_parallel": true,
"self": 1129.5745604429899
},
"steps_from_proto": {
"total": 92.2549531819842,
"count": 63757,
"is_parallel": true,
"self": 21.296565738953518,
"children": {
"_process_rank_one_or_two_observation": {
"total": 70.95838744303069,
"count": 510056,
"is_parallel": true,
"self": 70.95838744303069
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 733.5930202429878,
"count": 63758,
"self": 2.432698696975649,
"children": {
"process_trajectory": {
"total": 157.59123393401399,
"count": 63758,
"self": 157.20166932901373,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3895646050002597,
"count": 2,
"self": 0.3895646050002597
}
}
},
"_update_policy": {
"total": 573.5690876119982,
"count": 447,
"self": 221.7013058890061,
"children": {
"TorchPPOOptimizer.update": {
"total": 351.86778172299205,
"count": 22752,
"self": 351.86778172299205
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.139998837781604e-07,
"count": 1,
"self": 9.139998837781604e-07
},
"TrainerController._save_models": {
"total": 0.0840197329998773,
"count": 1,
"self": 0.0013766990000476653,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08264303399982964,
"count": 1,
"self": 0.08264303399982964
}
}
}
}
}
}
}