{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.37276285886764526, "min": 0.37276285886764526, "max": 1.4964677095413208, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11141.13671875, "min": 11141.13671875, "max": 45396.84375, "count": 33 }, "Pyramids.Step.mean": { "value": 989952.0, "min": 29952.0, "max": 989952.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989952.0, "min": 29952.0, "max": 989952.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5944133996963501, "min": -0.10207769274711609, "max": 0.6730814576148987, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 167.03016662597656, "min": -24.702800750732422, "max": 190.4820556640625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.008078553713858128, "min": -0.016677310690283775, "max": 0.4706823229789734, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -2.270073652267456, "min": -4.769711017608643, "max": 111.55171203613281, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06728277978485465, "min": 0.06505929724254132, "max": 0.07452829490771773, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9419589169879652, "min": 0.5136183031755045, "max": 1.0500602968865733, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.018761063877261543, "min": 0.0006374082541119545, "max": 0.018761063877261543, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2626548942816616, "min": 0.007648899049343454, "max": 0.276255791715812, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.241176157735716e-06, "min": 7.241176157735716e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010137646620830002, "min": 0.00010137646620830002, "max": 0.0035077334307555986, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10241369285714286, "min": 0.10241369285714286, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4337917, "min": 1.3886848, "max": 2.5692443999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025112791642857145, "min": 0.00025112791642857145, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035157908300000006, "min": 0.0035157908300000006, "max": 0.11694751556, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008098416961729527, "min": 0.008098416961729527, "max": 0.3290998041629791, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11337783932685852, "min": 0.11337783932685852, "max": 2.3036985397338867, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 294.37254901960785, "min": 269.3980582524272, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30026.0, "min": 15984.0, "max": 32883.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6637504806022834, "min": -1.0000000521540642, "max": 1.6982361748105004, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 168.0387985408306, "min": -30.754001662135124, "max": 178.31479835510254, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6637504806022834, "min": -1.0000000521540642, "max": 1.6982361748105004, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 168.0387985408306, "min": -30.754001662135124, "max": 178.31479835510254, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02470995312024111, "min": 0.024618531409518238, "max": 6.964528012089431, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.495705265144352, "min": 2.495705265144352, "max": 111.4324481934309, "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": "1685326692", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1685328930" }, "total": 2237.7078220759995, "count": 1, "self": 0.4904277469995577, "children": { "run_training.setup": { "total": 0.038170413999978337, "count": 1, "self": 0.038170413999978337 }, "TrainerController.start_learning": { "total": 2237.179223915, "count": 1, "self": 1.3083293730387595, "children": { "TrainerController._reset_env": { "total": 3.952754061000178, "count": 1, "self": 3.952754061000178 }, "TrainerController.advance": { "total": 2231.827563474961, "count": 64012, "self": 1.345359446916973, "children": { "env_step": { "total": 1592.200334197016, "count": 64012, "self": 1484.9756074140796, "children": { "SubprocessEnvManager._take_step": { "total": 106.45573378092581, "count": 64012, "self": 4.667062900914971, "children": { "TorchPolicy.evaluate": { "total": 101.78867088001084, "count": 62567, "self": 101.78867088001084 } } }, "workers": { "total": 0.7689930020105749, "count": 64012, "self": 0.0, "children": { "worker_root": { "total": 2232.4386428889993, "count": 64012, "is_parallel": true, "self": 859.2854925020395, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001852999999982785, "count": 1, "is_parallel": true, "self": 0.0005828850000852981, "children": { "_process_rank_one_or_two_observation": { "total": 0.001270114999897487, "count": 8, "is_parallel": true, "self": 0.001270114999897487 } } }, "UnityEnvironment.step": { "total": 0.04779091600016727, "count": 1, "is_parallel": true, "self": 0.0005822109999371605, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005043390001446824, "count": 1, "is_parallel": true, "self": 0.0005043390001446824 }, "communicator.exchange": { "total": 0.04492534600012732, "count": 1, "is_parallel": true, "self": 0.04492534600012732 }, "steps_from_proto": { "total": 0.0017790199999581091, "count": 1, "is_parallel": true, "self": 0.00037568999960058136, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014033300003575278, "count": 8, "is_parallel": true, "self": 0.0014033300003575278 } } } } } } }, "UnityEnvironment.step": { "total": 1373.1531503869599, "count": 64011, "is_parallel": true, "self": 31.980756223933895, "children": { "UnityEnvironment._generate_step_input": { "total": 22.839201045034542, "count": 64011, "is_parallel": true, "self": 22.839201045034542 }, "communicator.exchange": { "total": 1220.303337605945, "count": 64011, "is_parallel": true, "self": 1220.303337605945 }, "steps_from_proto": { "total": 98.02985551204642, "count": 64011, "is_parallel": true, "self": 19.654176114041547, "children": { "_process_rank_one_or_two_observation": { "total": 78.37567939800488, "count": 512088, "is_parallel": true, "self": 78.37567939800488 } } } } } } } } } } }, "trainer_advance": { "total": 638.2818698310282, "count": 64012, "self": 2.539241273027301, "children": { "process_trajectory": { "total": 110.13453325400087, "count": 64012, "self": 109.86244229400063, "children": { "RLTrainer._checkpoint": { "total": 0.27209096000024147, "count": 2, "self": 0.27209096000024147 } } }, "_update_policy": { "total": 525.608095304, "count": 450, "self": 337.0010840809939, "children": { "TorchPPOOptimizer.update": { "total": 188.6070112230061, "count": 22773, "self": 188.6070112230061 } } } } } } }, "trainer_threads": { "total": 9.589998626324814e-07, "count": 1, "self": 9.589998626324814e-07 }, "TrainerController._save_models": { "total": 0.0905760470000132, "count": 1, "self": 0.0013563980000981246, "children": { "RLTrainer._checkpoint": { "total": 0.08921964899991508, "count": 1, "self": 0.08921964899991508 } } } } } } }