{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3200460374355316, "min": 0.3200460374355316, "max": 1.462507724761963, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9637.2265625, "min": 9637.2265625, "max": 44366.6328125, "count": 33 }, "Pyramids.Step.mean": { "value": 989890.0, "min": 29952.0, "max": 989890.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989890.0, "min": 29952.0, "max": 989890.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.47800540924072266, "min": -0.16635718941688538, "max": 0.5213894248008728, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 129.06146240234375, "min": -39.42665481567383, "max": 140.775146484375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.019920695573091507, "min": -0.017448561266064644, "max": 0.3282035291194916, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.37858772277832, "min": -4.431934356689453, "max": 78.76884460449219, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06749906769869592, "min": 0.0640185922205726, "max": 0.07460406277850973, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0124860154804387, "min": 0.4931930050942324, "max": 1.0564806455536289, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01503419454190104, "min": 0.0006901170032580154, "max": 0.01590466577413701, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2255129181285156, "min": 0.008281404039096184, "max": 0.2255129181285156, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.415137528319999e-06, "min": 7.415137528319999e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011122706292479998, "min": 0.00011122706292479998, "max": 0.0034932067355977993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247168000000001, "min": 0.10247168000000001, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5370752, "min": 1.3691136000000002, "max": 2.4644022000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025692083200000004, "min": 0.00025692083200000004, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038538124800000005, "min": 0.0038538124800000005, "max": 0.11645377978000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010392609983682632, "min": 0.010392609983682632, "max": 0.4290338158607483, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15588915348052979, "min": 0.15588915348052979, "max": 3.003236770629883, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 402.6578947368421, "min": 366.04597701149424, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30602.0, "min": 15984.0, "max": 33743.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.465699980329526, "min": -1.0000000521540642, "max": 1.5514868184139854, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 111.39319850504398, "min": -32.000001668930054, "max": 130.14979819953442, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.465699980329526, "min": -1.0000000521540642, "max": 1.5514868184139854, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 111.39319850504398, "min": -32.000001668930054, "max": 130.14979819953442, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04363581134384731, "min": 0.04233522886000895, "max": 8.940964816138148, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.3163216621323954, "min": 3.3163216621323954, "max": 143.05543705821037, "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": "1688000920", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1688004442" }, "total": 3522.060382243, "count": 1, "self": 1.15904428299973, "children": { "run_training.setup": { "total": 0.05334236399994552, "count": 1, "self": 0.05334236399994552 }, "TrainerController.start_learning": { "total": 3520.847995596, "count": 1, "self": 2.4621161729978667, "children": { "TrainerController._reset_env": { "total": 1.510301360000085, "count": 1, "self": 1.510301360000085 }, "TrainerController.advance": { "total": 3516.760431553002, "count": 63658, "self": 2.499638835103724, "children": { "env_step": { "total": 2303.0695856410853, "count": 63658, "self": 2157.5151224702427, "children": { "SubprocessEnvManager._take_step": { "total": 144.0315624118307, "count": 63658, "self": 7.855224533897399, "children": { "TorchPolicy.evaluate": { "total": 136.1763378779333, "count": 62573, "self": 136.1763378779333 } } }, "workers": { "total": 1.5229007590119181, "count": 63658, "self": 0.0, "children": { "worker_root": { "total": 3513.063685583008, "count": 63658, "is_parallel": true, "self": 1537.8512296240224, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002911132000008365, "count": 1, "is_parallel": true, "self": 0.0010119440003109048, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018991879996974603, "count": 8, "is_parallel": true, "self": 0.0018991879996974603 } } }, "UnityEnvironment.step": { "total": 0.07543133099989063, "count": 1, "is_parallel": true, "self": 0.0006966229993849993, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000622244000169303, "count": 1, "is_parallel": true, "self": 0.000622244000169303 }, "communicator.exchange": { "total": 0.07180860300013592, "count": 1, "is_parallel": true, "self": 0.07180860300013592 }, "steps_from_proto": { "total": 0.0023038610002004134, "count": 1, "is_parallel": true, "self": 0.00044821699975727824, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018556440004431352, "count": 8, "is_parallel": true, "self": 0.0018556440004431352 } } } } } } }, "UnityEnvironment.step": { "total": 1975.2124559589856, "count": 63657, "is_parallel": true, "self": 47.74279305688742, "children": { "UnityEnvironment._generate_step_input": { "total": 27.598736543070572, "count": 63657, "is_parallel": true, "self": 27.598736543070572 }, "communicator.exchange": { "total": 1756.2620096161127, "count": 63657, "is_parallel": true, "self": 1756.2620096161127 }, "steps_from_proto": { "total": 143.60891674291497, "count": 63657, "is_parallel": true, "self": 30.643609754962654, "children": { "_process_rank_one_or_two_observation": { "total": 112.96530698795232, "count": 509256, "is_parallel": true, "self": 112.96530698795232 } } } } } } } } } } }, "trainer_advance": { "total": 1211.191207076813, "count": 63658, "self": 4.804064150690465, "children": { "process_trajectory": { "total": 155.41172877013014, "count": 63658, "self": 155.0884671841295, "children": { "RLTrainer._checkpoint": { "total": 0.32326158600062627, "count": 2, "self": 0.32326158600062627 } } }, "_update_policy": { "total": 1050.9754141559924, "count": 448, "self": 444.30026263890477, "children": { "TorchPPOOptimizer.update": { "total": 606.6751515170877, "count": 22815, "self": 606.6751515170877 } } } } } } }, "trainer_threads": { "total": 1.1309994079056196e-06, "count": 1, "self": 1.1309994079056196e-06 }, "TrainerController._save_models": { "total": 0.11514537900075084, "count": 1, "self": 0.0022285009999905014, "children": { "RLTrainer._checkpoint": { "total": 0.11291687800076033, "count": 1, "self": 0.11291687800076033 } } } } } } }