{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.28835752606391907, "min": 0.28835752606391907, "max": 1.4270148277282715, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8659.953125, "min": 8659.953125, "max": 43289.921875, "count": 33 }, "Pyramids.Step.mean": { "value": 989924.0, "min": 29951.0, "max": 989924.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989924.0, "min": 29951.0, "max": 989924.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6456658244132996, "min": -0.0864158645272255, "max": 0.684013843536377, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 187.2430877685547, "min": -20.912639617919922, "max": 197.67999267578125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01916155032813549, "min": 0.0019096247851848602, "max": 0.473260760307312, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.556849479675293, "min": 0.5518815517425537, "max": 112.16280364990234, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07187041853110572, "min": 0.06516774200523894, "max": 0.07392087714823715, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.00618585943548, "min": 0.5738891472315159, "max": 1.0973223444974898, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015296879213514311, "min": 0.000894682530945733, "max": 0.01697515641248578, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21415630898920035, "min": 0.010736190371348795, "max": 0.2546273461872867, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.330468985114292e-06, "min": 7.330468985114292e-06, "max": 0.0002950132891622375, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010262656579160008, "min": 0.00010262656579160008, "max": 0.0036353839882053997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244345714285716, "min": 0.10244345714285716, "max": 0.19833776250000004, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4342084000000002, "min": 1.4342084000000002, "max": 2.6117946, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025410136857142876, "min": 0.00025410136857142876, "max": 0.00983394247375, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003557419160000003, "min": 0.003557419160000003, "max": 0.12119828054, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01435818336904049, "min": 0.014300989918410778, "max": 0.5129237174987793, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.20101456344127655, "min": 0.20021386444568634, "max": 4.103389739990234, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 296.92929292929296, "min": 278.9126213592233, "max": 997.8387096774194, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29396.0, "min": 16878.0, "max": 34244.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6424444276425574, "min": -0.9342903754403514, "max": 1.6822407586337293, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 162.60199833661318, "min": -29.778401605784893, "max": 173.27079813927412, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6424444276425574, "min": -0.9342903754403514, "max": 1.6822407586337293, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 162.60199833661318, "min": -29.778401605784893, "max": 173.27079813927412, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04412483916126399, "min": 0.04237123936015177, "max": 10.880594050183015, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.368359076965135, "min": 4.017025554916472, "max": 184.97009885311127, "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": "1777279244", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1777281471" }, "total": 2226.9105745809998, "count": 1, "self": 0.4803811239994502, "children": { "run_training.setup": { "total": 0.035637721999819405, "count": 1, "self": 0.035637721999819405 }, "TrainerController.start_learning": { "total": 2226.3945557350003, "count": 1, "self": 1.3062946150071184, "children": { "TrainerController._reset_env": { "total": 2.514472656999942, "count": 1, "self": 2.514472656999942 }, "TrainerController.advance": { "total": 2222.497802134993, "count": 64109, "self": 1.3801407850082796, "children": { "env_step": { "total": 1569.046629918006, "count": 64109, "self": 1419.556328335069, "children": { "SubprocessEnvManager._take_step": { "total": 148.7264715509582, "count": 64109, "self": 4.529279873983796, "children": { "TorchPolicy.evaluate": { "total": 144.1971916769744, "count": 62574, "self": 144.1971916769744 } } }, "workers": { "total": 0.763830031978614, "count": 64109, "self": 0.0, "children": { "worker_root": { "total": 2220.2618548679634, "count": 64109, "is_parallel": true, "self": 917.226314325015, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002636360999986209, "count": 1, "is_parallel": true, "self": 0.0007584459999634419, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018779150000227673, "count": 8, "is_parallel": true, "self": 0.0018779150000227673 } } }, "UnityEnvironment.step": { "total": 0.09308665799994742, "count": 1, "is_parallel": true, "self": 0.0005667150001045229, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047878600003059546, "count": 1, "is_parallel": true, "self": 0.00047878600003059546 }, "communicator.exchange": { "total": 0.09026991799987627, "count": 1, "is_parallel": true, "self": 0.09026991799987627 }, "steps_from_proto": { "total": 0.0017712389999360312, "count": 1, "is_parallel": true, "self": 0.00035777399943981436, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014134650004962168, "count": 8, "is_parallel": true, "self": 0.0014134650004962168 } } } } } } }, "UnityEnvironment.step": { "total": 1303.0355405429484, "count": 64108, "is_parallel": true, "self": 33.5024895809006, "children": { "UnityEnvironment._generate_step_input": { "total": 23.57842505199551, "count": 64108, "is_parallel": true, "self": 23.57842505199551 }, "communicator.exchange": { "total": 1138.4629945740237, "count": 64108, "is_parallel": true, "self": 1138.4629945740237 }, "steps_from_proto": { "total": 107.4916313360286, "count": 64108, "is_parallel": true, "self": 22.349935216989024, "children": { "_process_rank_one_or_two_observation": { "total": 85.14169611903958, "count": 512864, "is_parallel": true, "self": 85.14169611903958 } } } } } } } } } } }, "trainer_advance": { "total": 652.071031431979, "count": 64109, "self": 2.518799171990622, "children": { "process_trajectory": { "total": 124.9403125009901, "count": 64109, "self": 124.75219245898984, "children": { "RLTrainer._checkpoint": { "total": 0.18812004200026422, "count": 2, "self": 0.18812004200026422 } } }, "_update_policy": { "total": 524.6119197589983, "count": 460, "self": 289.03781685099193, "children": { "TorchPPOOptimizer.update": { "total": 235.57410290800635, "count": 22800, "self": 235.57410290800635 } } } } } } }, "trainer_threads": { "total": 9.43000031838892e-07, "count": 1, "self": 9.43000031838892e-07 }, "TrainerController._save_models": { "total": 0.07598538499996721, "count": 1, "self": 0.0011760820002564287, "children": { "RLTrainer._checkpoint": { "total": 0.07480930299971078, "count": 1, "self": 0.07480930299971078 } } } } } } }