{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.15561535954475403, "min": 0.1443037986755371, "max": 1.491958498954773, "count": 133 }, "Pyramids.Policy.Entropy.sum": { "value": 4675.93017578125, "min": 4368.36474609375, "max": 45260.0546875, "count": 133 }, "Pyramids.Step.mean": { "value": 3989907.0, "min": 29952.0, "max": 3989907.0, "count": 133 }, "Pyramids.Step.sum": { "value": 3989907.0, "min": 29952.0, "max": 3989907.0, "count": 133 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7796312570571899, "min": -0.09474074095487595, "max": 0.8087203502655029, "count": 133 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 233.1097412109375, "min": -22.737777709960938, "max": 246.4840850830078, "count": 133 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0016256058588624, "min": -0.03237568587064743, "max": 0.28784438967704773, "count": 133 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.4860561490058899, "min": -9.12994384765625, "max": 68.21912384033203, "count": 133 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07272680058806492, "min": 0.06319011418670299, "max": 0.07417516935946954, "count": 133 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.018175208232909, "min": 0.5052633364914031, "max": 1.1126275403920431, "count": 133 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014127309161787187, "min": 6.117015439515597e-05, "max": 0.014444049657738238, "count": 133 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19778232826502062, "min": 0.0006728716983467156, "max": 0.21533731706971165, "count": 133 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.850376168955361e-06, "min": 1.850376168955361e-06, "max": 0.0002987876575469714, "count": 133 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.5905266365375056e-05, "min": 2.5905266365375056e-05, "max": 0.00394291113569635, "count": 133 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10061675892857144, "min": 0.10061675892857144, "max": 0.19959588571428571, "count": 133 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4086346250000001, "min": 1.3971712, "max": 2.8143036500000003, "count": 133 }, "Pyramids.Policy.Beta.mean": { "value": 7.161421696428583e-05, "min": 7.161421696428583e-05, "max": 0.009959628982857143, "count": 133 }, "Pyramids.Policy.Beta.sum": { "value": 0.0010025990375000017, "min": 0.0010025990375000017, "max": 0.131448934635, "count": 133 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.003568369662389159, "min": 0.0034553383011370897, "max": 0.39232689142227173, "count": 133 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.04995717480778694, "min": 0.048374734818935394, "max": 2.746288299560547, "count": 133 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 249.92, "min": 227.5793650793651, "max": 999.0, "count": 133 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31240.0, "min": 15984.0, "max": 34000.0, "count": 133 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6860559906363488, "min": -1.0000000521540642, "max": 1.7724206174413364, "count": 133 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 210.7569988295436, "min": -31.99760165810585, "max": 233.67099763453007, "count": 133 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6860559906363488, "min": -1.0000000521540642, "max": 1.7724206174413364, "count": 133 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 210.7569988295436, "min": -31.99760165810585, "max": 233.67099763453007, "count": 133 }, "Pyramids.Policy.RndReward.mean": { "value": 0.009245664918329568, "min": 0.008796961532890807, "max": 7.6557459738105536, "count": 133 }, "Pyramids.Policy.RndReward.sum": { "value": 1.1557081147911958, "min": 1.0450589459796902, "max": 122.49193558096886, "count": 133 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 133 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 133 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1697628764", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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 Training1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1697637987" }, "total": 9223.120932598, "count": 1, "self": 0.4788704410002538, "children": { "run_training.setup": { "total": 0.057555171999865706, "count": 1, "self": 0.057555171999865706 }, "TrainerController.start_learning": { "total": 9222.584506985, "count": 1, "self": 7.891989266139717, "children": { "TrainerController._reset_env": { "total": 1.113580094000099, "count": 1, "self": 1.113580094000099 }, "TrainerController.advance": { "total": 9213.52281046086, "count": 259216, "self": 7.231042925022848, "children": { "env_step": { "total": 6386.965831334122, "count": 259216, "self": 5941.50298067712, "children": { "SubprocessEnvManager._take_step": { "total": 440.8336664113831, "count": 259216, "self": 17.726295058277174, "children": { "TorchPolicy.evaluate": { "total": 423.1073713531059, "count": 250069, "self": 423.1073713531059 } } }, "workers": { "total": 4.629184245618944, "count": 259216, "self": 0.0, "children": { "worker_root": { "total": 9206.452853194902, "count": 259216, "is_parallel": true, "self": 3778.7059417669843, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0030201690001376846, "count": 1, "is_parallel": true, "self": 0.0009753089998412179, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020448600002964668, "count": 8, "is_parallel": true, "self": 0.0020448600002964668 } } }, "UnityEnvironment.step": { "total": 0.07747701800008144, "count": 1, "is_parallel": true, "self": 0.0004940790004184237, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005145599998286343, "count": 1, "is_parallel": true, "self": 0.0005145599998286343 }, "communicator.exchange": { "total": 0.07477559899962216, "count": 1, "is_parallel": true, "self": 0.07477559899962216 }, "steps_from_proto": { "total": 0.001692780000212224, "count": 1, "is_parallel": true, "self": 0.0004361239989520982, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012566560012601258, "count": 8, "is_parallel": true, "self": 0.0012566560012601258 } } } } } } }, "UnityEnvironment.step": { "total": 5427.746911427917, "count": 259215, "is_parallel": true, "self": 131.921891382588, "children": { "UnityEnvironment._generate_step_input": { "total": 78.2736829626524, "count": 259215, "is_parallel": true, "self": 78.2736829626524 }, "communicator.exchange": { "total": 4846.374181114703, "count": 259215, "is_parallel": true, "self": 4846.374181114703 }, "steps_from_proto": { "total": 371.17715596797416, "count": 259215, "is_parallel": true, "self": 81.04575311939834, "children": { "_process_rank_one_or_two_observation": { "total": 290.1314028485758, "count": 2073720, "is_parallel": true, "self": 290.1314028485758 } } } } } } } } } } }, "trainer_advance": { "total": 2819.325936201714, "count": 259216, "self": 14.066478092523539, "children": { "process_trajectory": { "total": 443.2608636722239, "count": 259216, "self": 442.7413865342228, "children": { "RLTrainer._checkpoint": { "total": 0.5194771380010934, "count": 8, "self": 0.5194771380010934 } } }, "_update_policy": { "total": 2361.9985944369664, "count": 1860, "self": 950.941966650948, "children": { "TorchPPOOptimizer.update": { "total": 1411.0566277860185, "count": 91263, "self": 1411.0566277860185 } } } } } } }, "trainer_threads": { "total": 9.799987310543656e-07, "count": 1, "self": 9.799987310543656e-07 }, "TrainerController._save_models": { "total": 0.05612618400118663, "count": 1, "self": 0.001119930000641034, "children": { "RLTrainer._checkpoint": { "total": 0.055006254000545596, "count": 1, "self": 0.055006254000545596 } } } } } } }