{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4217751622200012, "min": 0.4068375527858734, "max": 1.47845458984375, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12801.7197265625, "min": 11990.31640625, "max": 44850.3984375, "count": 33 }, "Pyramids.Step.mean": { "value": 989946.0, "min": 29952.0, "max": 989946.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989946.0, "min": 29952.0, "max": 989946.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.451963871717453, "min": -0.17323777079582214, "max": 0.47231289744377136, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 122.03024291992188, "min": -41.057350158691406, "max": 126.1075439453125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.008978008292615414, "min": -0.004839690867811441, "max": 0.35996198654174805, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.4240622520446777, "min": -1.2534799575805664, "max": 85.31098937988281, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06924364245066247, "min": 0.06569798657291044, "max": 0.07373504016182086, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9694109943092746, "min": 0.49024346816800424, "max": 1.0714295787426331, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014895434157681717, "min": 0.0005694680698887781, "max": 0.015097129851654584, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20853607820754405, "min": 0.0076621221479226485, "max": 0.2113598179231642, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.483447505550003e-06, "min": 7.483447505550003e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010476826507770005, "min": 0.00010476826507770005, "max": 0.0032529410156863993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249445, "min": 0.10249445, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4349223, "min": 1.3886848, "max": 2.4825376999999995, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025919555500000016, "min": 0.00025919555500000016, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036287377700000025, "min": 0.0036287377700000025, "max": 0.10845292863999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00949426181614399, "min": 0.009307535365223885, "max": 0.46683362126350403, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13291966915130615, "min": 0.13030549883842468, "max": 3.2678353786468506, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 415.72972972972974, "min": 388.79487179487177, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30764.0, "min": 15984.0, "max": 32511.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4761161902869069, "min": -1.0000000521540642, "max": 1.4829563884398875, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 109.23259808123112, "min": -30.280401691794395, "max": 115.67059829831123, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4761161902869069, "min": -1.0000000521540642, "max": 1.4829563884398875, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 109.23259808123112, "min": -30.280401691794395, "max": 115.67059829831123, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04040351385098089, "min": 0.04040351385098089, "max": 9.792980520054698, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.989860024972586, "min": 2.9346383853117004, "max": 156.68768832087517, "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": "1688248177", "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/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "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": "1688250364" }, "total": 2186.29032398, "count": 1, "self": 0.42435851399977764, "children": { "run_training.setup": { "total": 0.037924023999948986, "count": 1, "self": 0.037924023999948986 }, "TrainerController.start_learning": { "total": 2185.828041442, "count": 1, "self": 1.3484907879451384, "children": { "TrainerController._reset_env": { "total": 4.051695628000061, "count": 1, "self": 4.051695628000061 }, "TrainerController.advance": { "total": 2180.334058860055, "count": 63640, "self": 1.3587807850553872, "children": { "env_step": { "total": 1549.6816942379787, "count": 63640, "self": 1443.9187377100927, "children": { "SubprocessEnvManager._take_step": { "total": 105.00415598791642, "count": 63640, "self": 4.585051514953875, "children": { "TorchPolicy.evaluate": { "total": 100.41910447296254, "count": 62573, "self": 100.41910447296254 } } }, "workers": { "total": 0.7588005399695703, "count": 63640, "self": 0.0, "children": { "worker_root": { "total": 2180.8577556869714, "count": 63640, "is_parallel": true, "self": 845.7583590819461, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001730210999994597, "count": 1, "is_parallel": true, "self": 0.000553399999944304, "children": { "_process_rank_one_or_two_observation": { "total": 0.001176811000050293, "count": 8, "is_parallel": true, "self": 0.001176811000050293 } } }, "UnityEnvironment.step": { "total": 0.04622939899991252, "count": 1, "is_parallel": true, "self": 0.0005357149998417299, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047806500015212805, "count": 1, "is_parallel": true, "self": 0.00047806500015212805 }, "communicator.exchange": { "total": 0.04335449099994548, "count": 1, "is_parallel": true, "self": 0.04335449099994548 }, "steps_from_proto": { "total": 0.0018611279999731778, "count": 1, "is_parallel": true, "self": 0.0003802669996275654, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014808610003456124, "count": 8, "is_parallel": true, "self": 0.0014808610003456124 } } } } } } }, "UnityEnvironment.step": { "total": 1335.0993966050253, "count": 63639, "is_parallel": true, "self": 32.544493379963114, "children": { "UnityEnvironment._generate_step_input": { "total": 22.04633948601213, "count": 63639, "is_parallel": true, "self": 22.04633948601213 }, "communicator.exchange": { "total": 1182.0679232290468, "count": 63639, "is_parallel": true, "self": 1182.0679232290468 }, "steps_from_proto": { "total": 98.44064051000328, "count": 63639, "is_parallel": true, "self": 19.161251931808692, "children": { "_process_rank_one_or_two_observation": { "total": 79.27938857819458, "count": 509112, "is_parallel": true, "self": 79.27938857819458 } } } } } } } } } } }, "trainer_advance": { "total": 629.2935838370206, "count": 63640, "self": 2.4441643889829265, "children": { "process_trajectory": { "total": 104.18556769904103, "count": 63640, "self": 103.9859959030407, "children": { "RLTrainer._checkpoint": { "total": 0.1995717960003276, "count": 2, "self": 0.1995717960003276 } } }, "_update_policy": { "total": 522.6638517489966, "count": 446, "self": 338.7466357519868, "children": { "TorchPPOOptimizer.update": { "total": 183.91721599700986, "count": 22863, "self": 183.91721599700986 } } } } } } }, "trainer_threads": { "total": 9.159998626273591e-07, "count": 1, "self": 9.159998626273591e-07 }, "TrainerController._save_models": { "total": 0.09379525000031208, "count": 1, "self": 0.0017884540002341964, "children": { "RLTrainer._checkpoint": { "total": 0.09200679600007788, "count": 1, "self": 0.09200679600007788 } } } } } } }