{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5928608775138855, "min": 0.5556651949882507, "max": 1.4590778350830078, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17653.025390625, "min": 16678.845703125, "max": 44262.5859375, "count": 33 }, "Pyramids.Step.mean": { "value": 989924.0, "min": 29946.0, "max": 989924.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989924.0, "min": 29946.0, "max": 989924.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4902063012123108, "min": -0.1351797878742218, "max": 0.5038336515426636, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 131.3752899169922, "min": -32.0376091003418, "max": 138.08917236328125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03605698049068451, "min": 0.0025259454268962145, "max": 0.26475656032562256, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 9.663270950317383, "min": 0.6921090483665466, "max": 63.80632781982422, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06928511761940548, "min": 0.06508688571531131, "max": 0.07518144640129147, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9699916466716767, "min": 0.5484958463481305, "max": 1.0778128475786242, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014268014535397725, "min": 0.00010588859806464147, "max": 0.015645395393944928, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19975220349556816, "min": 0.0012706631767756976, "max": 0.21903553551522897, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.5909331840071444e-06, "min": 7.5909331840071444e-06, "max": 0.00029520682659772495, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010627306457610002, "min": 0.00010627306457610002, "max": 0.0031393340535554003, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253027857142857, "min": 0.10253027857142857, "max": 0.19840227500000002, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4354239, "min": 1.4354239, "max": 2.3464446000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026277482928571433, "min": 0.00026277482928571433, "max": 0.0098403872725, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036788476100000004, "min": 0.0036788476100000004, "max": 0.10466981554, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00921603012830019, "min": 0.00921603012830019, "max": 0.3853369355201721, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1290244162082672, "min": 0.1290244162082672, "max": 3.082695484161377, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 426.0144927536232, "min": 365.0125, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29395.0, "min": 15978.0, "max": 32896.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5159999846980192, "min": -0.9999600519736608, "max": 1.5849699751473962, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 104.60399894416332, "min": -31.99760165810585, "max": 126.7975980117917, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5159999846980192, "min": -0.9999600519736608, "max": 1.5849699751473962, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 104.60399894416332, "min": -31.99760165810585, "max": 126.7975980117917, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04115787389657825, "min": 0.03742182587297975, "max": 8.750770568847656, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.839893298863899, "min": 2.839893298863899, "max": 140.0123291015625, "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": "1743417635", "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": "1743419817" }, "total": 2181.8923656099996, "count": 1, "self": 0.4882553949996691, "children": { "run_training.setup": { "total": 0.020086215999981505, "count": 1, "self": 0.020086215999981505 }, "TrainerController.start_learning": { "total": 2181.384023999, "count": 1, "self": 1.35726221400364, "children": { "TrainerController._reset_env": { "total": 2.2054292710001846, "count": 1, "self": 2.2054292710001846 }, "TrainerController.advance": { "total": 2177.735376859996, "count": 63525, "self": 1.3773539519688711, "children": { "env_step": { "total": 1497.549242758987, "count": 63525, "self": 1346.3150958979952, "children": { "SubprocessEnvManager._take_step": { "total": 150.46253648099037, "count": 63525, "self": 4.4674607769029535, "children": { "TorchPolicy.evaluate": { "total": 145.9950757040874, "count": 62559, "self": 145.9950757040874 } } }, "workers": { "total": 0.771610380001448, "count": 63525, "self": 0.0, "children": { "worker_root": { "total": 2176.422575733035, "count": 63525, "is_parallel": true, "self": 939.5261733780414, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019832079999559937, "count": 1, "is_parallel": true, "self": 0.0007175279997682082, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012656800001877855, "count": 8, "is_parallel": true, "self": 0.0012656800001877855 } } }, "UnityEnvironment.step": { "total": 0.05035158300006515, "count": 1, "is_parallel": true, "self": 0.0005378260002544266, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046174599992809817, "count": 1, "is_parallel": true, "self": 0.00046174599992809817 }, "communicator.exchange": { "total": 0.04775298999993538, "count": 1, "is_parallel": true, "self": 0.04775298999993538 }, "steps_from_proto": { "total": 0.0015990209999472427, "count": 1, "is_parallel": true, "self": 0.0003305639997961407, "children": { "_process_rank_one_or_two_observation": { "total": 0.001268457000151102, "count": 8, "is_parallel": true, "self": 0.001268457000151102 } } } } } } }, "UnityEnvironment.step": { "total": 1236.8964023549936, "count": 63524, "is_parallel": true, "self": 31.027808357896447, "children": { "UnityEnvironment._generate_step_input": { "total": 22.38758811705202, "count": 63524, "is_parallel": true, "self": 22.38758811705202 }, "communicator.exchange": { "total": 1091.0487639550372, "count": 63524, "is_parallel": true, "self": 1091.0487639550372 }, "steps_from_proto": { "total": 92.43224192500793, "count": 63524, "is_parallel": true, "self": 18.470683458001986, "children": { "_process_rank_one_or_two_observation": { "total": 73.96155846700594, "count": 508192, "is_parallel": true, "self": 73.96155846700594 } } } } } } } } } } }, "trainer_advance": { "total": 678.8087801490401, "count": 63525, "self": 2.524726408070592, "children": { "process_trajectory": { "total": 125.18227238697, "count": 63525, "self": 124.92925847597007, "children": { "RLTrainer._checkpoint": { "total": 0.25301391099992543, "count": 2, "self": 0.25301391099992543 } } }, "_update_policy": { "total": 551.1017813539995, "count": 442, "self": 303.723287517985, "children": { "TorchPPOOptimizer.update": { "total": 247.3784938360145, "count": 22869, "self": 247.3784938360145 } } } } } } }, "trainer_threads": { "total": 9.469999895372894e-07, "count": 1, "self": 9.469999895372894e-07 }, "TrainerController._save_models": { "total": 0.08595470700038277, "count": 1, "self": 0.0014626850002059655, "children": { "RLTrainer._checkpoint": { "total": 0.0844920220001768, "count": 1, "self": 0.0844920220001768 } } } } } } }