{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.44614899158477783, "min": 0.44614899158477783, "max": 1.4700690507888794, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13370.193359375, "min": 13370.193359375, "max": 44596.015625, "count": 33 }, "Pyramids.Step.mean": { "value": 989989.0, "min": 29952.0, "max": 989989.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989989.0, "min": 29952.0, "max": 989989.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.48446834087371826, "min": -0.18910780549049377, "max": 0.6047989726066589, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 131.775390625, "min": -44.81855010986328, "max": 169.34371948242188, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.033756665885448456, "min": -0.033756665885448456, "max": 0.2392277866601944, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -9.18181324005127, "min": -9.18181324005127, "max": 57.414669036865234, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06753492383609733, "min": 0.06373329285252231, "max": 0.07447250496227951, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0130238575414598, "min": 0.47268125324158106, "max": 1.07625700601299, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016197190474162602, "min": 0.0003741686825424954, "max": 0.016197190474162602, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24295785711243903, "min": 0.0029933494603399634, "max": 0.24295785711243903, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.532797489100001e-06, "min": 7.532797489100001e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011299196233650001, "min": 0.00011299196233650001, "max": 0.0033820877726374998, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251089999999999, "min": 0.10251089999999999, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5376634999999998, "min": 1.3691136000000002, "max": 2.5273625, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026083891000000005, "min": 0.00026083891000000005, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003912583650000001, "min": 0.003912583650000001, "max": 0.11276351374999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008596601895987988, "min": 0.008596601895987988, "max": 0.3137284815311432, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12894903123378754, "min": 0.12261345982551575, "max": 2.196099281311035, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 379.1375, "min": 326.3695652173913, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30331.0, "min": 15984.0, "max": 31968.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.445814974233508, "min": -1.0000000521540642, "max": 1.6495591231411504, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 115.66519793868065, "min": -32.000001668930054, "max": 153.40899845212698, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.445814974233508, "min": -1.0000000521540642, "max": 1.6495591231411504, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 115.66519793868065, "min": -32.000001668930054, "max": 153.40899845212698, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0340312399159302, "min": 0.03209903886227528, "max": 5.823149872943759, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.722499193274416, "min": 2.5570553019060753, "max": 93.17039796710014, "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": "1704566673", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.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": "1704568881" }, "total": 2208.370972848, "count": 1, "self": 0.5268066379994707, "children": { "run_training.setup": { "total": 0.04545845999996345, "count": 1, "self": 0.04545845999996345 }, "TrainerController.start_learning": { "total": 2207.79870775, "count": 1, "self": 1.3553776900212142, "children": { "TrainerController._reset_env": { "total": 2.132984846999989, "count": 1, "self": 2.132984846999989 }, "TrainerController.advance": { "total": 2204.224066228979, "count": 63796, "self": 1.3907053410771368, "children": { "env_step": { "total": 1559.5580277029444, "count": 63796, "self": 1430.5523279710178, "children": { "SubprocessEnvManager._take_step": { "total": 128.16989797594465, "count": 63796, "self": 4.582762986877697, "children": { "TorchPolicy.evaluate": { "total": 123.58713498906695, "count": 62569, "self": 123.58713498906695 } } }, "workers": { "total": 0.8358017559819473, "count": 63796, "self": 0.0, "children": { "worker_root": { "total": 2202.556591174958, "count": 63796, "is_parallel": true, "self": 890.0121236548805, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017165599999771075, "count": 1, "is_parallel": true, "self": 0.0005246340003850491, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011919259995920584, "count": 8, "is_parallel": true, "self": 0.0011919259995920584 } } }, "UnityEnvironment.step": { "total": 0.052607783999974345, "count": 1, "is_parallel": true, "self": 0.0006694300000162912, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004954900000484486, "count": 1, "is_parallel": true, "self": 0.0004954900000484486 }, "communicator.exchange": { "total": 0.049695707999944716, "count": 1, "is_parallel": true, "self": 0.049695707999944716 }, "steps_from_proto": { "total": 0.001747155999964889, "count": 1, "is_parallel": true, "self": 0.00039426199987246946, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013528940000924194, "count": 8, "is_parallel": true, "self": 0.0013528940000924194 } } } } } } }, "UnityEnvironment.step": { "total": 1312.5444675200777, "count": 63795, "is_parallel": true, "self": 35.22807180312907, "children": { "UnityEnvironment._generate_step_input": { "total": 24.07115893492687, "count": 63795, "is_parallel": true, "self": 24.07115893492687 }, "communicator.exchange": { "total": 1154.1816629049529, "count": 63795, "is_parallel": true, "self": 1154.1816629049529 }, "steps_from_proto": { "total": 99.06357387706885, "count": 63795, "is_parallel": true, "self": 19.556759960974432, "children": { "_process_rank_one_or_two_observation": { "total": 79.50681391609442, "count": 510360, "is_parallel": true, "self": 79.50681391609442 } } } } } } } } } } }, "trainer_advance": { "total": 643.2753331849578, "count": 63796, "self": 2.6018723819122442, "children": { "process_trajectory": { "total": 125.21429681804216, "count": 63796, "self": 124.90320399104189, "children": { "RLTrainer._checkpoint": { "total": 0.31109282700026597, "count": 2, "self": 0.31109282700026597 } } }, "_update_policy": { "total": 515.4591639850034, "count": 442, "self": 306.8743806869877, "children": { "TorchPPOOptimizer.update": { "total": 208.58478329801574, "count": 22860, "self": 208.58478329801574 } } } } } } }, "trainer_threads": { "total": 9.79000105871819e-07, "count": 1, "self": 9.79000105871819e-07 }, "TrainerController._save_models": { "total": 0.08627800499971272, "count": 1, "self": 0.0014404609996745421, "children": { "RLTrainer._checkpoint": { "total": 0.08483754400003818, "count": 1, "self": 0.08483754400003818 } } } } } } }