{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6913639307022095, "min": 0.6807979345321655, "max": 1.5183219909667969, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 20740.91796875, "min": 20423.9375, "max": 46059.81640625, "count": 33 }, "Pyramids.Step.mean": { "value": 989924.0, "min": 29952.0, "max": 989924.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989924.0, "min": 29952.0, "max": 989924.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.20129531621932983, "min": -0.13373512029647827, "max": 0.20129531621932983, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 51.33030700683594, "min": -31.69522476196289, "max": 51.33030700683594, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.013980908319354057, "min": -0.05154495686292648, "max": 0.2703520655632019, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -3.565131664276123, "min": -12.937784194946289, "max": 64.07344055175781, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06798828124609667, "min": 0.06421265105921264, "max": 0.07283667660642766, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9518359374453534, "min": 0.49039784042166695, "max": 1.0432544064613323, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.007759642990563776, "min": 0.00011295626906233294, "max": 0.008942335689685674, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.10863500186789286, "min": 0.0014684314978103282, "max": 0.12519269965559943, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.65084744975e-06, "min": 7.65084744975e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001071118642965, "min": 0.0001071118642965, "max": 0.0030216965927679002, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255025000000002, "min": 0.10255025000000002, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4357035000000002, "min": 1.3691136000000002, "max": 2.3072321000000002, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026476997500000005, "min": 0.00026476997500000005, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037067796500000003, "min": 0.0037067796500000003, "max": 0.10075248678999997, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011857847683131695, "min": 0.011429036036133766, "max": 0.3653551936149597, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16600987315177917, "min": 0.16000650823116302, "max": 2.5574862957000732, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 661.0816326530612, "min": 639.2826086956521, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32393.0, "min": 15984.0, "max": 32413.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.6791124644999703, "min": -1.0000000521540642, "max": 0.7083130028584729, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 32.59739829599857, "min": -32.000001668930054, "max": 32.59739829599857, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.6791124644999703, "min": -1.0000000521540642, "max": 0.7083130028584729, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 32.59739829599857, "min": -32.000001668930054, "max": 32.59739829599857, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.08081953146150529, "min": 0.07828857509593945, "max": 7.081630400381982, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.8793375101522543, "min": 3.508715468691662, "max": 113.30608640611172, "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": "1739589091", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1739592062" }, "total": 2970.544901956, "count": 1, "self": 0.6347414580000077, "children": { "run_training.setup": { "total": 0.0363617970000405, "count": 1, "self": 0.0363617970000405 }, "TrainerController.start_learning": { "total": 2969.873798701, "count": 1, "self": 2.3931772859664306, "children": { "TrainerController._reset_env": { "total": 3.40054928699999, "count": 1, "self": 3.40054928699999 }, "TrainerController.advance": { "total": 2963.9980465770336, "count": 63221, "self": 2.3385225339638964, "children": { "env_step": { "total": 1899.1079108229694, "count": 63221, "self": 1735.822659021967, "children": { "SubprocessEnvManager._take_step": { "total": 161.9474087539901, "count": 63221, "self": 6.517275140983429, "children": { "TorchPolicy.evaluate": { "total": 155.43013361300666, "count": 62568, "self": 155.43013361300666 } } }, "workers": { "total": 1.3378430470122566, "count": 63221, "self": 0.0, "children": { "worker_root": { "total": 2962.8447243310206, "count": 63221, "is_parallel": true, "self": 1392.0379128000177, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006175393999910739, "count": 1, "is_parallel": true, "self": 0.004150149999986752, "children": { "_process_rank_one_or_two_observation": { "total": 0.002025243999923987, "count": 8, "is_parallel": true, "self": 0.002025243999923987 } } }, "UnityEnvironment.step": { "total": 0.06153402000006736, "count": 1, "is_parallel": true, "self": 0.0006652440001744253, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005367569999634725, "count": 1, "is_parallel": true, "self": 0.0005367569999634725 }, "communicator.exchange": { "total": 0.05834507199995187, "count": 1, "is_parallel": true, "self": 0.05834507199995187 }, "steps_from_proto": { "total": 0.00198694699997759, "count": 1, "is_parallel": true, "self": 0.0005589420001115286, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014280049998660616, "count": 8, "is_parallel": true, "self": 0.0014280049998660616 } } } } } } }, "UnityEnvironment.step": { "total": 1570.806811531003, "count": 63220, "is_parallel": true, "self": 44.23472342996229, "children": { "UnityEnvironment._generate_step_input": { "total": 29.16921319200253, "count": 63220, "is_parallel": true, "self": 29.16921319200253 }, "communicator.exchange": { "total": 1375.7555031360425, "count": 63220, "is_parallel": true, "self": 1375.7555031360425 }, "steps_from_proto": { "total": 121.64737177299537, "count": 63220, "is_parallel": true, "self": 26.428034123023735, "children": { "_process_rank_one_or_two_observation": { "total": 95.21933764997164, "count": 505760, "is_parallel": true, "self": 95.21933764997164 } } } } } } } } } } }, "trainer_advance": { "total": 1062.5516132201005, "count": 63221, "self": 4.061315938058215, "children": { "process_trajectory": { "total": 155.63963185304488, "count": 63221, "self": 155.30712347704525, "children": { "RLTrainer._checkpoint": { "total": 0.33250837599962324, "count": 2, "self": 0.33250837599962324 } } }, "_update_policy": { "total": 902.8506654289974, "count": 427, "self": 357.3207624990075, "children": { "TorchPPOOptimizer.update": { "total": 545.5299029299899, "count": 22848, "self": 545.5299029299899 } } } } } } }, "trainer_threads": { "total": 1.3409999155555852e-06, "count": 1, "self": 1.3409999155555852e-06 }, "TrainerController._save_models": { "total": 0.08202420999987226, "count": 1, "self": 0.0019679239999277343, "children": { "RLTrainer._checkpoint": { "total": 0.08005628599994452, "count": 1, "self": 0.08005628599994452 } } } } } } }