{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.752404510974884, "min": 0.7446481585502625, "max": 1.4475173950195312, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 22475.828125, "min": 22220.30078125, "max": 43911.88671875, "count": 33 }, "Pyramids.Step.mean": { "value": 989914.0, "min": 29952.0, "max": 989914.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989914.0, "min": 29952.0, "max": 989914.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.39320582151412964, "min": -0.1025870218873024, "max": 0.4089769124984741, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 106.16557312011719, "min": -24.723472595214844, "max": 110.42376708984375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.012855459935963154, "min": -0.03745002672076225, "max": 0.3895516097545624, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -3.4709742069244385, "min": -9.774456977844238, "max": 92.32373046875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06731963285989147, "min": 0.0657065052671667, "max": 0.070955144798777, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.009794492898372, "min": 0.48059778338115555, "max": 1.0360445273886025, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01494436897462412, "min": 0.000490965161048273, "max": 0.01494436897462412, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2241655346193618, "min": 0.0049096516104827305, "max": 0.2241655346193618, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.48501751508e-06, "min": 2.48501751508e-06, "max": 9.838354447360002e-05, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 3.7275262726200006e-05, "min": 3.7275262726200006e-05, "max": 0.0010851785148216998, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248492, "min": 0.10248492, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5372738, "min": 1.3886848, "max": 2.4840030000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025824350800000004, "min": 0.00025824350800000004, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003873652620000001, "min": 0.003873652620000001, "max": 0.10853931216999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008831266313791275, "min": 0.008831266313791275, "max": 0.3580308258533478, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13246899843215942, "min": 0.12596070766448975, "max": 2.506215810775757, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 444.5147058823529, "min": 435.015873015873, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30227.0, "min": 15984.0, "max": 33629.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.378970569547485, "min": -1.0000000521540642, "max": 1.408266638834325, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 93.76999872922897, "min": -31.99920167028904, "max": 93.76999872922897, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.378970569547485, "min": -1.0000000521540642, "max": 1.408266638834325, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 93.76999872922897, "min": -31.99920167028904, "max": 93.76999872922897, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04124646667621752, "min": 0.04124646667621752, "max": 8.720934831537306, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.8047597339827917, "min": 2.8047597339827917, "max": 139.5349573045969, "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": "1705114713", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1705118565" }, "total": 3852.379509343, "count": 1, "self": 0.7309545810003328, "children": { "run_training.setup": { "total": 0.09398214199973154, "count": 1, "self": 0.09398214199973154 }, "TrainerController.start_learning": { "total": 3851.55457262, "count": 1, "self": 2.4573126248706103, "children": { "TrainerController._reset_env": { "total": 2.999534611000854, "count": 1, "self": 2.999534611000854 }, "TrainerController.advance": { "total": 3846.004651636127, "count": 63481, "self": 2.8149224512944784, "children": { "env_step": { "total": 2138.822948975987, "count": 63481, "self": 1962.8046567361998, "children": { "SubprocessEnvManager._take_step": { "total": 174.36495148488757, "count": 63481, "self": 6.9447794237712515, "children": { "TorchPolicy.evaluate": { "total": 167.42017206111632, "count": 62575, "self": 167.42017206111632 } } }, "workers": { "total": 1.6533407548995456, "count": 63481, "self": 0.0, "children": { "worker_root": { "total": 3844.9061464941024, "count": 63481, "is_parallel": true, "self": 2072.589791339935, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003106320000370033, "count": 1, "is_parallel": true, "self": 0.0012031769983877894, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019031430019822437, "count": 8, "is_parallel": true, "self": 0.0019031430019822437 } } }, "UnityEnvironment.step": { "total": 0.0873848370010819, "count": 1, "is_parallel": true, "self": 0.0007657940004719421, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005388680001487955, "count": 1, "is_parallel": true, "self": 0.0005388680001487955 }, "communicator.exchange": { "total": 0.08392997200098762, "count": 1, "is_parallel": true, "self": 0.08392997200098762 }, "steps_from_proto": { "total": 0.0021502029994735494, "count": 1, "is_parallel": true, "self": 0.00044258400339458603, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017076189960789634, "count": 8, "is_parallel": true, "self": 0.0017076189960789634 } } } } } } }, "UnityEnvironment.step": { "total": 1772.3163551541675, "count": 63480, "is_parallel": true, "self": 49.35308143341172, "children": { "UnityEnvironment._generate_step_input": { "total": 28.064904663837297, "count": 63480, "is_parallel": true, "self": 28.064904663837297 }, "communicator.exchange": { "total": 1560.754516314113, "count": 63480, "is_parallel": true, "self": 1560.754516314113 }, "steps_from_proto": { "total": 134.1438527428054, "count": 63480, "is_parallel": true, "self": 29.099854613930802, "children": { "_process_rank_one_or_two_observation": { "total": 105.04399812887459, "count": 507840, "is_parallel": true, "self": 105.04399812887459 } } } } } } } } } } }, "trainer_advance": { "total": 1704.3667802088457, "count": 63481, "self": 5.318831624765153, "children": { "process_trajectory": { "total": 176.11431703810194, "count": 63481, "self": 175.86328792510176, "children": { "RLTrainer._checkpoint": { "total": 0.25102911300018604, "count": 2, "self": 0.25102911300018604 } } }, "_update_policy": { "total": 1522.9336315459786, "count": 444, "self": 627.9782676730065, "children": { "TorchPPOOptimizer.update": { "total": 894.9553638729722, "count": 38010, "self": 894.9553638729722 } } } } } } }, "trainer_threads": { "total": 1.0250005288980901e-06, "count": 1, "self": 1.0250005288980901e-06 }, "TrainerController._save_models": { "total": 0.09307272300065961, "count": 1, "self": 0.002401848001682083, "children": { "RLTrainer._checkpoint": { "total": 0.09067087499897752, "count": 1, "self": 0.09067087499897752 } } } } } } }