{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.12108424305915833, "min": 0.10761411488056183, "max": 1.1241554021835327, "count": 98 }, "Pyramids.Policy.Entropy.sum": { "value": 3607.341796875, "min": 3221.5361328125, "max": 33670.703125, "count": 98 }, "Pyramids.Step.mean": { "value": 2999923.0, "min": 89946.0, "max": 2999923.0, "count": 98 }, "Pyramids.Step.sum": { "value": 2999923.0, "min": 89946.0, "max": 2999923.0, "count": 98 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8025296330451965, "min": -0.07234443724155426, "max": 0.8686206936836243, "count": 98 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 240.75889587402344, "min": -17.435009002685547, "max": 259.71759033203125, "count": 98 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03190188109874725, "min": -0.032362714409828186, "max": 0.22596928477287292, "count": 98 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 9.570564270019531, "min": -8.349580764770508, "max": 49.71324157714844, "count": 98 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06961067153218511, "min": 0.062464789440301025, "max": 0.07442919098006116, "count": 98 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0441600729827767, "min": 0.5000451286738181, "max": 1.0737962459679693, "count": 98 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017002342539166826, "min": 0.0010650644952976119, "max": 0.017906734493509345, "count": 98 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2550351380875024, "min": 0.010584445343090335, "max": 0.2686010174026402, "count": 98 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.494952835048888e-06, "min": 1.494952835048888e-06, "max": 0.00029218514546209526, "count": 98 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.242429252573332e-05, "min": 2.242429252573332e-05, "max": 0.003969721676759467, "count": 98 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10049828444444445, "min": 0.10049828444444445, "max": 0.1973950476190476, "count": 98 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5074742666666667, "min": 1.3817653333333333, "max": 2.7974938333333337, "count": 98 }, "Pyramids.Policy.Beta.mean": { "value": 5.9778615999999974e-05, "min": 5.9778615999999974e-05, "max": 0.009739765257142858, "count": 98 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008966792399999996, "min": 0.0008966792399999996, "max": 0.13233172928, "count": 98 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00801317673176527, "min": 0.007838928140699863, "max": 0.126565620303154, "count": 98 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12019764631986618, "min": 0.10974498838186264, "max": 0.9957698583602905, "count": 98 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 228.62790697674419, "min": 206.2246376811594, "max": 972.0625, "count": 98 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29493.0, "min": 16520.0, "max": 33250.0, "count": 98 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7403550206344256, "min": -0.8550588769071242, "max": 1.785697832060375, "count": 98 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 224.50579766184092, "min": -27.125201672315598, "max": 248.2119986563921, "count": 98 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7403550206344256, "min": -0.8550588769071242, "max": 1.785697832060375, "count": 98 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 224.50579766184092, "min": -27.125201672315598, "max": 248.2119986563921, "count": 98 }, "Pyramids.Policy.RndReward.mean": { "value": 0.018986398641150013, "min": 0.018836452563898976, "max": 1.390013551010805, "count": 98 }, "Pyramids.Policy.RndReward.sum": { "value": 2.4492454247083515, "min": 2.4492454247083515, "max": 34.241594422608614, "count": 98 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 98 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 98 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1682426481", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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 --resume", "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": "1682433715" }, "total": 7234.442442271999, "count": 1, "self": 0.5788218669977141, "children": { "run_training.setup": { "total": 0.10635580000007394, "count": 1, "self": 0.10635580000007394 }, "TrainerController.start_learning": { "total": 7233.757264605001, "count": 1, "self": 4.287620990709911, "children": { "TrainerController._reset_env": { "total": 3.7976574859999346, "count": 1, "self": 3.7976574859999346 }, "TrainerController.advance": { "total": 7225.574284348291, "count": 191370, "self": 4.421769595035585, "children": { "env_step": { "total": 5397.507338442952, "count": 191370, "self": 5078.588448034961, "children": { "SubprocessEnvManager._take_step": { "total": 316.30131566609634, "count": 191370, "self": 14.07713459933666, "children": { "TorchPolicy.evaluate": { "total": 302.2241810667597, "count": 183661, "self": 302.2241810667597 } } }, "workers": { "total": 2.617574741894259, "count": 191370, "self": 0.0, "children": { "worker_root": { "total": 7217.166731911255, "count": 191370, "is_parallel": true, "self": 2477.9400633559053, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020443610001166235, "count": 1, "is_parallel": true, "self": 0.0005535679993045051, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014907930008121184, "count": 8, "is_parallel": true, "self": 0.0014907930008121184 } } }, "UnityEnvironment.step": { "total": 0.062171978000151285, "count": 1, "is_parallel": true, "self": 0.0005401860003075853, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004526880002231337, "count": 1, "is_parallel": true, "self": 0.0004526880002231337 }, "communicator.exchange": { "total": 0.05956863999972484, "count": 1, "is_parallel": true, "self": 0.05956863999972484 }, "steps_from_proto": { "total": 0.0016104639998957282, "count": 1, "is_parallel": true, "self": 0.00038403299913625233, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012264310007594759, "count": 8, "is_parallel": true, "self": 0.0012264310007594759 } } } } } } }, "UnityEnvironment.step": { "total": 4739.2266685553495, "count": 191369, "is_parallel": true, "self": 96.53126280003744, "children": { "UnityEnvironment._generate_step_input": { "total": 67.2611834970935, "count": 191369, "is_parallel": true, "self": 67.2611834970935 }, "communicator.exchange": { "total": 4294.5784620030445, "count": 191369, "is_parallel": true, "self": 4294.5784620030445 }, "steps_from_proto": { "total": 280.85576025517366, "count": 191369, "is_parallel": true, "self": 60.70517340107608, "children": { "_process_rank_one_or_two_observation": { "total": 220.15058685409758, "count": 1530952, "is_parallel": true, "self": 220.15058685409758 } } } } } } } } } } }, "trainer_advance": { "total": 1823.6451763103046, "count": 191370, "self": 8.693880619180618, "children": { "process_trajectory": { "total": 323.6267087870988, "count": 191370, "self": 322.94043303709896, "children": { "RLTrainer._checkpoint": { "total": 0.6862757499998224, "count": 6, "self": 0.6862757499998224 } } }, "_update_policy": { "total": 1491.3245869040252, "count": 1379, "self": 949.5559885099392, "children": { "TorchPPOOptimizer.update": { "total": 541.768598394086, "count": 66930, "self": 541.768598394086 } } } } } } }, "trainer_threads": { "total": 9.929990483215079e-07, "count": 1, "self": 9.929990483215079e-07 }, "TrainerController._save_models": { "total": 0.09770078700057638, "count": 1, "self": 0.002078694002193515, "children": { "RLTrainer._checkpoint": { "total": 0.09562209299838287, "count": 1, "self": 0.09562209299838287 } } } } } } }