ppo-Huggy / run_logs /timers.json
carova's picture
Huggy
d7e1fbb
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4041985273361206,
"min": 1.4041985273361206,
"max": 1.4304393529891968,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70542.71875,
"min": 67494.546875,
"max": 78645.890625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 131.70712401055408,
"min": 100.77189409368636,
"max": 410.40983606557376,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49917.0,
"min": 49113.0,
"max": 50187.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999585.0,
"min": 49927.0,
"max": 1999585.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999585.0,
"min": 49927.0,
"max": 1999585.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.271411180496216,
"min": 0.02993684448301792,
"max": 2.367011785507202,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 860.8648681640625,
"min": 3.6223580837249756,
"max": 1150.4241943359375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.461562357351459,
"min": 1.7239693346594975,
"max": 3.723681266547418,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1311.932133436203,
"min": 208.6002894937992,
"max": 1802.310476720333,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.461562357351459,
"min": 1.7239693346594975,
"max": 3.723681266547418,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1311.932133436203,
"min": 208.6002894937992,
"max": 1802.310476720333,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016900918677371618,
"min": 0.014191310989068976,
"max": 0.02027665311096219,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.033801837354743236,
"min": 0.028382621978137953,
"max": 0.05549983057402035,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.037401436517635986,
"min": 0.021971182183672985,
"max": 0.07633563540875912,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.07480287303527197,
"min": 0.04394236436734597,
"max": 0.20207035603622597,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.401023533024995e-06,
"min": 4.401023533024995e-06,
"max": 0.00029527635157455,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.80204706604999e-06,
"min": 8.80204706604999e-06,
"max": 0.0008438794687068501,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10146697499999999,
"min": 0.10146697499999999,
"max": 0.19842545000000006,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20293394999999997,
"min": 0.20293394999999997,
"max": 0.58129315,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.320205249999989e-05,
"min": 8.320205249999989e-05,
"max": 0.004921429955000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00016640410499999978,
"min": 0.00016640410499999978,
"max": 0.014066528185000003,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1689103316",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics --force",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1689105959"
},
"total": 2643.6653770360003,
"count": 1,
"self": 0.43848452600013843,
"children": {
"run_training.setup": {
"total": 0.042289793999771064,
"count": 1,
"self": 0.042289793999771064
},
"TrainerController.start_learning": {
"total": 2643.1846027160004,
"count": 1,
"self": 4.835558625070007,
"children": {
"TrainerController._reset_env": {
"total": 4.11780759200019,
"count": 1,
"self": 4.11780759200019
},
"TrainerController.advance": {
"total": 2634.0977813539303,
"count": 230704,
"self": 4.95779072591813,
"children": {
"env_step": {
"total": 2062.94257481418,
"count": 230704,
"self": 1736.8272144242328,
"children": {
"SubprocessEnvManager._take_step": {
"total": 322.9775018610426,
"count": 230704,
"self": 18.295622792096765,
"children": {
"TorchPolicy.evaluate": {
"total": 304.6818790689458,
"count": 223092,
"self": 304.6818790689458
}
}
},
"workers": {
"total": 3.1378585289044167,
"count": 230704,
"self": 0.0,
"children": {
"worker_root": {
"total": 2634.968048691083,
"count": 230704,
"is_parallel": true,
"self": 1216.2104829278896,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0034224360001644527,
"count": 1,
"is_parallel": true,
"self": 0.0003003480001098069,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003122088000054646,
"count": 2,
"is_parallel": true,
"self": 0.003122088000054646
}
}
},
"UnityEnvironment.step": {
"total": 0.02918543799978579,
"count": 1,
"is_parallel": true,
"self": 0.00032352399966839585,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023460700003852253,
"count": 1,
"is_parallel": true,
"self": 0.00023460700003852253
},
"communicator.exchange": {
"total": 0.02786397299996679,
"count": 1,
"is_parallel": true,
"self": 0.02786397299996679
},
"steps_from_proto": {
"total": 0.0007633340001120814,
"count": 1,
"is_parallel": true,
"self": 0.00022335699986797408,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005399770002441073,
"count": 2,
"is_parallel": true,
"self": 0.0005399770002441073
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1418.7575657631933,
"count": 230703,
"is_parallel": true,
"self": 41.1638564541372,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 91.47764297207186,
"count": 230703,
"is_parallel": true,
"self": 91.47764297207186
},
"communicator.exchange": {
"total": 1183.1293658380519,
"count": 230703,
"is_parallel": true,
"self": 1183.1293658380519
},
"steps_from_proto": {
"total": 102.98670049893235,
"count": 230703,
"is_parallel": true,
"self": 38.90510752678756,
"children": {
"_process_rank_one_or_two_observation": {
"total": 64.08159297214479,
"count": 461406,
"is_parallel": true,
"self": 64.08159297214479
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 566.1974158138323,
"count": 230704,
"self": 7.154031742841653,
"children": {
"process_trajectory": {
"total": 143.62588045599432,
"count": 230704,
"self": 142.26880184499487,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3570786109994515,
"count": 10,
"self": 1.3570786109994515
}
}
},
"_update_policy": {
"total": 415.41750361499635,
"count": 96,
"self": 353.5163100920131,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.90119352298325,
"count": 2880,
"self": 61.90119352298325
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.4600000011269e-07,
"count": 1,
"self": 9.4600000011269e-07
},
"TrainerController._save_models": {
"total": 0.13345419899997069,
"count": 1,
"self": 0.0020662040005845483,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13138799499938614,
"count": 1,
"self": 0.13138799499938614
}
}
}
}
}
}
}