{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.14061538875102997, "min": 0.14053569734096527, "max": 1.3911505937576294, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4265.70849609375, "min": 4180.09375, "max": 42201.9453125, "count": 100 }, "Pyramids.Step.mean": { "value": 2999926.0, "min": 29972.0, "max": 2999926.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999926.0, "min": 29972.0, "max": 2999926.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.807197630405426, "min": -0.13647176325321198, "max": 0.932406485080719, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 242.96649169921875, "min": -32.48027801513672, "max": 290.91082763671875, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0010257521644234657, "min": -0.056847888976335526, "max": 0.3367462456226349, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.3087514042854309, "min": -16.201648712158203, "max": 80.1456069946289, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06880765477054675, "min": 0.06426263314677358, "max": 0.07728716898738687, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9633071667876544, "min": 0.5410101829117081, "max": 1.0579855681668657, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01478279261201384, "min": 0.0004311523526813211, "max": 0.016575085549404667, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20695909656819375, "min": 0.005173828232175853, "max": 0.23205119769166535, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.507935211673807e-06, "min": 1.507935211673807e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.11110929634333e-05, "min": 2.11110929634333e-05, "max": 0.0039692235769255, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10050261190476191, "min": 0.10050261190476191, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4070365666666667, "min": 1.3962282666666668, "max": 2.7826482000000006, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.0210929285714204e-05, "min": 6.0210929285714204e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008429530099999989, "min": 0.0008429530099999989, "max": 0.13231514255, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006910176016390324, "min": 0.006357233505696058, "max": 0.40948158502578735, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09674246609210968, "min": 0.09354124218225479, "max": 2.8663711547851562, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 230.51937984496124, "min": 197.82119205298014, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29737.0, "min": 16771.0, "max": 32954.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.737915367919665, "min": -0.9998875516466796, "max": 1.8028609139832439, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 225.92899782955647, "min": -31.99640165269375, "max": 272.23199801146984, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.737915367919665, "min": -0.9998875516466796, "max": 1.8028609139832439, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 225.92899782955647, "min": -31.99640165269375, "max": 272.23199801146984, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.016769580352746952, "min": 0.014540918192664457, "max": 7.970142076997196, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.180045445857104, "min": 2.0097714929488575, "max": 135.49241530895233, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1718296226", "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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1718303777" }, "total": 7551.441627581, "count": 1, "self": 0.5273597360001077, "children": { "run_training.setup": { "total": 0.052221433999875444, "count": 1, "self": 0.052221433999875444 }, "TrainerController.start_learning": { "total": 7550.862046411, "count": 1, "self": 4.686683353977969, "children": { "TrainerController._reset_env": { "total": 2.796456985000077, "count": 1, "self": 2.796456985000077 }, "TrainerController.advance": { "total": 7543.283796013023, "count": 195464, "self": 4.828877217181798, "children": { "env_step": { "total": 5602.119653650033, "count": 195464, "self": 5192.990015998542, "children": { "SubprocessEnvManager._take_step": { "total": 406.3406295155173, "count": 195464, "self": 15.001277419299186, "children": { "TorchPolicy.evaluate": { "total": 391.33935209621814, "count": 187564, "self": 391.33935209621814 } } }, "workers": { "total": 2.789008135973745, "count": 195464, "self": 0.0, "children": { "worker_root": { "total": 7534.844538606305, "count": 195464, "is_parallel": true, "self": 2726.448744892392, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021334250004656496, "count": 1, "is_parallel": true, "self": 0.0006300240011114511, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015034009993541986, "count": 8, "is_parallel": true, "self": 0.0015034009993541986 } } }, "UnityEnvironment.step": { "total": 0.06097591100024147, "count": 1, "is_parallel": true, "self": 0.0006512510008178651, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043672299943864346, "count": 1, "is_parallel": true, "self": 0.00043672299943864346 }, "communicator.exchange": { "total": 0.05834196300020267, "count": 1, "is_parallel": true, "self": 0.05834196300020267 }, "steps_from_proto": { "total": 0.0015459739997822908, "count": 1, "is_parallel": true, "self": 0.00034939099987241207, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011965829999098787, "count": 8, "is_parallel": true, "self": 0.0011965829999098787 } } } } } } }, "UnityEnvironment.step": { "total": 4808.395793713913, "count": 195463, "is_parallel": true, "self": 105.76069712940352, "children": { "UnityEnvironment._generate_step_input": { "total": 70.27108647788828, "count": 195463, "is_parallel": true, "self": 70.27108647788828 }, "communicator.exchange": { "total": 4328.382695832093, "count": 195463, "is_parallel": true, "self": 4328.382695832093 }, "steps_from_proto": { "total": 303.9813142745279, "count": 195463, "is_parallel": true, "self": 63.71803043797536, "children": { "_process_rank_one_or_two_observation": { "total": 240.26328383655255, "count": 1563704, "is_parallel": true, "self": 240.26328383655255 } } } } } } } } } } }, "trainer_advance": { "total": 1936.335265145808, "count": 195464, "self": 8.797877780706585, "children": { "process_trajectory": { "total": 401.64328510906034, "count": 195464, "self": 401.08283152105923, "children": { "RLTrainer._checkpoint": { "total": 0.5604535880011099, "count": 6, "self": 0.5604535880011099 } } }, "_update_policy": { "total": 1525.8941022560412, "count": 1400, "self": 903.7323140879398, "children": { "TorchPPOOptimizer.update": { "total": 622.1617881681013, "count": 68364, "self": 622.1617881681013 } } } } } } }, "trainer_threads": { "total": 9.300001693191007e-07, "count": 1, "self": 9.300001693191007e-07 }, "TrainerController._save_models": { "total": 0.0951091289989563, "count": 1, "self": 0.0018302979988220613, "children": { "RLTrainer._checkpoint": { "total": 0.09327883100013423, "count": 1, "self": 0.09327883100013423 } } } } } } }