{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.31118911504745483, "min": 0.30987805128097534, "max": 1.4798107147216797, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9405.3798828125, "min": 9261.634765625, "max": 44891.5390625, "count": 33 }, "Pyramids.Step.mean": { "value": 989971.0, "min": 29952.0, "max": 989971.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989971.0, "min": 29952.0, "max": 989971.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6827241778373718, "min": -0.18512026965618134, "max": 0.7158223390579224, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 193.2109375, "min": -43.873504638671875, "max": 208.30430603027344, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.019785964861512184, "min": 0.0022637764923274517, "max": 0.3247827887535095, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.599428176879883, "min": 0.574999213218689, "max": 76.97351837158203, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06358976356638041, "min": 0.06358976356638041, "max": 0.07413574998715834, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.8902566899293257, "min": 0.4627963032750092, "max": 1.0391918089607153, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014123367347998456, "min": 0.0002900175242562183, "max": 0.01801295071310874, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19772714287197837, "min": 0.0023201401940497464, "max": 0.25218130998352234, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.578654616671431e-06, "min": 7.578654616671431e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010610116463340003, "min": 0.00010610116463340003, "max": 0.0033834743721753, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252618571428572, "min": 0.10252618571428572, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4353666, "min": 1.327104, "max": 2.5278247, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026236595285714293, "min": 0.00026236595285714293, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003673123340000001, "min": 0.003673123340000001, "max": 0.11280968753000004, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010815544985234737, "min": 0.010815544985234737, "max": 0.44237253069877625, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15141762793064117, "min": 0.15141762793064117, "max": 3.0966076850891113, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 278.13, "min": 248.27272727272728, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27813.0, "min": 15984.0, "max": 31968.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6818519852310418, "min": -1.0000000521540642, "max": 1.7258636211807077, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 168.1851985231042, "min": -32.000001668930054, "max": 207.9571982100606, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6818519852310418, "min": -1.0000000521540642, "max": 1.7258636211807077, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 168.1851985231042, "min": -32.000001668930054, "max": 207.9571982100606, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.030918405601732958, "min": 0.028007515557235383, "max": 9.338343483395875, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.0918405601732957, "min": 3.0918405601732957, "max": 149.413495734334, "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": "1735155516", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1735157111" }, "total": 1594.686857048, "count": 1, "self": 0.32290964999992866, "children": { "run_training.setup": { "total": 0.05529550699975516, "count": 1, "self": 0.05529550699975516 }, "TrainerController.start_learning": { "total": 1594.3086518910004, "count": 1, "self": 1.0989483202201882, "children": { "TrainerController._reset_env": { "total": 4.828269435000038, "count": 1, "self": 4.828269435000038 }, "TrainerController.advance": { "total": 1588.2962982707804, "count": 64305, "self": 1.128837062790808, "children": { "env_step": { "total": 1008.9481471770187, "count": 64305, "self": 887.9773703100982, "children": { "SubprocessEnvManager._take_step": { "total": 120.30348505102847, "count": 64305, "self": 3.933692541923847, "children": { "TorchPolicy.evaluate": { "total": 116.36979250910463, "count": 62570, "self": 116.36979250910463 } } }, "workers": { "total": 0.6672918158919856, "count": 64305, "self": 0.0, "children": { "worker_root": { "total": 1592.5287438390314, "count": 64305, "is_parallel": true, "self": 787.4921015800564, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002048862000265217, "count": 1, "is_parallel": true, "self": 0.0006436590010707732, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014052029991944437, "count": 8, "is_parallel": true, "self": 0.0014052029991944437 } } }, "UnityEnvironment.step": { "total": 0.035248400999989826, "count": 1, "is_parallel": true, "self": 0.0004088339992449619, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002974990002257982, "count": 1, "is_parallel": true, "self": 0.0002974990002257982 }, "communicator.exchange": { "total": 0.03357177900034003, "count": 1, "is_parallel": true, "self": 0.03357177900034003 }, "steps_from_proto": { "total": 0.0009702890001790365, "count": 1, "is_parallel": true, "self": 0.00022150299901113613, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007487860011679004, "count": 8, "is_parallel": true, "self": 0.0007487860011679004 } } } } } } }, "UnityEnvironment.step": { "total": 805.036642258975, "count": 64304, "is_parallel": true, "self": 20.112847677958598, "children": { "UnityEnvironment._generate_step_input": { "total": 13.30974388001141, "count": 64304, "is_parallel": true, "self": 13.30974388001141 }, "communicator.exchange": { "total": 714.3880361340607, "count": 64304, "is_parallel": true, "self": 714.3880361340607 }, "steps_from_proto": { "total": 57.226014566944286, "count": 64304, "is_parallel": true, "self": 12.015926416107504, "children": { "_process_rank_one_or_two_observation": { "total": 45.21008815083678, "count": 514432, "is_parallel": true, "self": 45.21008815083678 } } } } } } } } } } }, "trainer_advance": { "total": 578.219314030971, "count": 64305, "self": 2.0897318569031995, "children": { "process_trajectory": { "total": 111.83856276807819, "count": 64305, "self": 111.60626052707721, "children": { "RLTrainer._checkpoint": { "total": 0.23230224100097985, "count": 2, "self": 0.23230224100097985 } } }, "_update_policy": { "total": 464.2910194059896, "count": 438, "self": 255.22920347094168, "children": { "TorchPPOOptimizer.update": { "total": 209.0618159350479, "count": 22821, "self": 209.0618159350479 } } } } } } }, "trainer_threads": { "total": 9.57999873207882e-07, "count": 1, "self": 9.57999873207882e-07 }, "TrainerController._save_models": { "total": 0.08513490699988324, "count": 1, "self": 0.0014799549999224837, "children": { "RLTrainer._checkpoint": { "total": 0.08365495199996076, "count": 1, "self": 0.08365495199996076 } } } } } } }