{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.31149953603744507, "min": 0.31149953603744507, "max": 1.5054049491882324, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9240.322265625, "min": 9240.322265625, "max": 45667.96484375, "count": 33 }, "Pyramids.Step.mean": { "value": 989999.0, "min": 29952.0, "max": 989999.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989999.0, "min": 29952.0, "max": 989999.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5664092302322388, "min": -0.08925566077232361, "max": 0.621580958366394, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 156.32894897460938, "min": -21.421358108520508, "max": 177.73406982421875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.01701180450618267, "min": -0.01701180450618267, "max": 0.2739257514476776, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -4.695258140563965, "min": -4.695258140563965, "max": 64.92040252685547, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06974016503185856, "min": 0.06475338852185196, "max": 0.07266470423909333, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0461024754778785, "min": 0.49969235278502766, "max": 1.0488053988297263, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01631732677651374, "min": 0.00043589524960384817, "max": 0.016319147356192668, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24475990164770606, "min": 0.0034871619968307854, "max": 0.24475990164770606, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.448017517360004e-06, "min": 7.448017517360004e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011172026276040006, "min": 0.00011172026276040006, "max": 0.0033798326733891996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248264000000001, "min": 0.10248264000000001, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5372396000000002, "min": 1.3691136000000002, "max": 2.5266108, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025801573600000015, "min": 0.00025801573600000015, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003870236040000002, "min": 0.003870236040000002, "max": 0.11268841891999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006922535132616758, "min": 0.006922535132616758, "max": 0.3583793044090271, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10383802652359009, "min": 0.09947595000267029, "max": 2.508655071258545, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 327.96590909090907, "min": 311.78, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28861.0, "min": 15984.0, "max": 32607.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6492977044121786, "min": -1.0000000521540642, "max": 1.686135400707523, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 145.1381979882717, "min": -32.000001668930054, "max": 162.8201985359192, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6492977044121786, "min": -1.0000000521540642, "max": 1.686135400707523, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 145.1381979882717, "min": -32.000001668930054, "max": 162.8201985359192, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02363273614826705, "min": 0.023066475686012684, "max": 7.290255395695567, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.0796807810475, "min": 2.0796807810475, "max": 116.64408633112907, "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": "1745405681", "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=PyramidsTraining --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": "1745409184" }, "total": 3502.399443611, "count": 1, "self": 0.8616084939999382, "children": { "run_training.setup": { "total": 0.0251284130000613, "count": 1, "self": 0.0251284130000613 }, "TrainerController.start_learning": { "total": 3501.5127067040003, "count": 1, "self": 2.448035442998844, "children": { "TrainerController._reset_env": { "total": 3.475324412999953, "count": 1, "self": 3.475324412999953 }, "TrainerController.advance": { "total": 3495.496224503002, "count": 64152, "self": 2.527061338976182, "children": { "env_step": { "total": 2360.910764074025, "count": 64152, "self": 2188.4673556669877, "children": { "SubprocessEnvManager._take_step": { "total": 171.0563418580241, "count": 64152, "self": 7.500303754998072, "children": { "TorchPolicy.evaluate": { "total": 163.55603810302603, "count": 62557, "self": 163.55603810302603 } } }, "workers": { "total": 1.3870665490129568, "count": 64152, "self": 0.0, "children": { "worker_root": { "total": 3493.6942606029643, "count": 64152, "is_parallel": true, "self": 1483.4353514479599, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0061989729999822885, "count": 1, "is_parallel": true, "self": 0.00469746299995677, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015015100000255188, "count": 8, "is_parallel": true, "self": 0.0015015100000255188 } } }, "UnityEnvironment.step": { "total": 0.06917131499994866, "count": 1, "is_parallel": true, "self": 0.0006635390000155894, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000505793000002086, "count": 1, "is_parallel": true, "self": 0.000505793000002086 }, "communicator.exchange": { "total": 0.06587512799990236, "count": 1, "is_parallel": true, "self": 0.06587512799990236 }, "steps_from_proto": { "total": 0.002126855000028627, "count": 1, "is_parallel": true, "self": 0.0004565320001574946, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016703229998711322, "count": 8, "is_parallel": true, "self": 0.0016703229998711322 } } } } } } }, "UnityEnvironment.step": { "total": 2010.2589091550044, "count": 64151, "is_parallel": true, "self": 45.659849706987416, "children": { "UnityEnvironment._generate_step_input": { "total": 31.555541570010405, "count": 64151, "is_parallel": true, "self": 31.555541570010405 }, "communicator.exchange": { "total": 1804.8428072129761, "count": 64151, "is_parallel": true, "self": 1804.8428072129761 }, "steps_from_proto": { "total": 128.20071066503056, "count": 64151, "is_parallel": true, "self": 28.07377664898354, "children": { "_process_rank_one_or_two_observation": { "total": 100.12693401604702, "count": 513208, "is_parallel": true, "self": 100.12693401604702 } } } } } } } } } } }, "trainer_advance": { "total": 1132.0583990900009, "count": 64152, "self": 4.662982029972454, "children": { "process_trajectory": { "total": 168.1223440760216, "count": 64152, "self": 167.68798442102138, "children": { "RLTrainer._checkpoint": { "total": 0.43435965500020757, "count": 2, "self": 0.43435965500020757 } } }, "_update_policy": { "total": 959.2730729840068, "count": 445, "self": 371.6692763780454, "children": { "TorchPPOOptimizer.update": { "total": 587.6037966059614, "count": 22830, "self": 587.6037966059614 } } } } } } }, "trainer_threads": { "total": 1.1419997463235632e-06, "count": 1, "self": 1.1419997463235632e-06 }, "TrainerController._save_models": { "total": 0.0931212030000097, "count": 1, "self": 0.0023389979996863985, "children": { "RLTrainer._checkpoint": { "total": 0.0907822050003233, "count": 1, "self": 0.0907822050003233 } } } } } } }