{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5390892624855042, "min": 0.5390892624855042, "max": 1.5593442916870117, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16241.681640625, "min": 16241.681640625, "max": 47304.26953125, "count": 33 }, "Pyramids.Step.mean": { "value": 989961.0, "min": 29952.0, "max": 989961.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989961.0, "min": 29952.0, "max": 989961.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3679182529449463, "min": -0.2248402237892151, "max": 0.40893039107322693, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 97.49833679199219, "min": -53.287132263183594, "max": 107.54869079589844, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.3092624843120575, "min": -0.3092624843120575, "max": 0.15915042161941528, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -81.95455932617188, "min": -81.95455932617188, "max": 37.718650817871094, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0663803664124711, "min": 0.06521619034166214, "max": 0.07437726868137172, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9293251297745954, "min": 0.47215893594651814, "max": 1.0587588445838156, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.02464498167960084, "min": 7.168061418446273e-05, "max": 0.02464498167960084, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.3450297435144118, "min": 0.0008601673702135527, "max": 0.3450297435144118, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.675511727242859e-06, "min": 7.675511727242859e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010745716418140003, "min": 0.00010745716418140003, "max": 0.0031381799539400997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255847142857144, "min": 0.10255847142857144, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358186000000002, "min": 1.3691136000000002, "max": 2.3460599, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026559129571428577, "min": 0.00026559129571428577, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037182781400000005, "min": 0.0037182781400000005, "max": 0.10463138401000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005210391245782375, "min": 0.005210391245782375, "max": 0.21293902397155762, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.0729454755783081, "min": 0.0729454755783081, "max": 1.4905731678009033, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 484.57142857142856, "min": 475.41269841269843, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30528.0, "min": 15984.0, "max": 33288.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2843491780379461, "min": -1.0000000521540642, "max": 1.4055841003382017, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 80.91399821639061, "min": -32.000001668930054, "max": 88.5517983213067, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2843491780379461, "min": -1.0000000521540642, "max": 1.4055841003382017, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 80.91399821639061, "min": -32.000001668930054, "max": 88.5517983213067, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.026754732689744466, "min": 0.02612496932528706, "max": 4.479016438592225, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 1.6855481594539015, "min": 1.6458730674930848, "max": 71.6642630174756, "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": "1703602748", "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": "1703604907" }, "total": 2158.59164945, "count": 1, "self": 0.4766006190002372, "children": { "run_training.setup": { "total": 0.06884812099997362, "count": 1, "self": 0.06884812099997362 }, "TrainerController.start_learning": { "total": 2158.04620071, "count": 1, "self": 1.5453916851010945, "children": { "TrainerController._reset_env": { "total": 2.1010409140003503, "count": 1, "self": 2.1010409140003503 }, "TrainerController.advance": { "total": 2154.3108202428984, "count": 63461, "self": 1.5989859000410434, "children": { "env_step": { "total": 1525.7365561059319, "count": 63461, "self": 1385.7640349640114, "children": { "SubprocessEnvManager._take_step": { "total": 139.0374795229368, "count": 63461, "self": 5.088378932812702, "children": { "TorchPolicy.evaluate": { "total": 133.9491005901241, "count": 62572, "self": 133.9491005901241 } } }, "workers": { "total": 0.9350416189836324, "count": 63461, "self": 0.0, "children": { "worker_root": { "total": 2152.544307878044, "count": 63461, "is_parallel": true, "self": 895.5127977370353, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018347079999330163, "count": 1, "is_parallel": true, "self": 0.0005834559997310862, "children": { "_process_rank_one_or_two_observation": { "total": 0.00125125200020193, "count": 8, "is_parallel": true, "self": 0.00125125200020193 } } }, "UnityEnvironment.step": { "total": 0.051021830000081536, "count": 1, "is_parallel": true, "self": 0.0006035650003468618, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005106270000396762, "count": 1, "is_parallel": true, "self": 0.0005106270000396762 }, "communicator.exchange": { "total": 0.04820219099974565, "count": 1, "is_parallel": true, "self": 0.04820219099974565 }, "steps_from_proto": { "total": 0.001705446999949345, "count": 1, "is_parallel": true, "self": 0.0003689579998535919, "children": { "_process_rank_one_or_two_observation": { "total": 0.001336489000095753, "count": 8, "is_parallel": true, "self": 0.001336489000095753 } } } } } } }, "UnityEnvironment.step": { "total": 1257.0315101410088, "count": 63460, "is_parallel": true, "self": 35.89969953806394, "children": { "UnityEnvironment._generate_step_input": { "total": 25.958572241024285, "count": 63460, "is_parallel": true, "self": 25.958572241024285 }, "communicator.exchange": { "total": 1089.9492681559586, "count": 63460, "is_parallel": true, "self": 1089.9492681559586 }, "steps_from_proto": { "total": 105.2239702059619, "count": 63460, "is_parallel": true, "self": 21.632838686037758, "children": { "_process_rank_one_or_two_observation": { "total": 83.59113151992415, "count": 507680, "is_parallel": true, "self": 83.59113151992415 } } } } } } } } } } }, "trainer_advance": { "total": 626.9752782369255, "count": 63461, "self": 2.757885666922448, "children": { "process_trajectory": { "total": 127.07920654500049, "count": 63461, "self": 126.89430934300026, "children": { "RLTrainer._checkpoint": { "total": 0.1848972020002293, "count": 2, "self": 0.1848972020002293 } } }, "_update_policy": { "total": 497.1381860250026, "count": 434, "self": 293.10731915304996, "children": { "TorchPPOOptimizer.update": { "total": 204.03086687195264, "count": 22848, "self": 204.03086687195264 } } } } } } }, "trainer_threads": { "total": 1.4090001059230417e-06, "count": 1, "self": 1.4090001059230417e-06 }, "TrainerController._save_models": { "total": 0.08894645899999887, "count": 1, "self": 0.001974519000214059, "children": { "RLTrainer._checkpoint": { "total": 0.08697193999978481, "count": 1, "self": 0.08697193999978481 } } } } } } }