{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2613027095794678, "min": 0.2613027095794678, "max": 1.430524230003357, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 7818.1767578125, "min": 7818.1767578125, "max": 43396.3828125, "count": 33 }, "Pyramids.Step.mean": { "value": 989927.0, "min": 29952.0, "max": 989927.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989927.0, "min": 29952.0, "max": 989927.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5187909007072449, "min": -0.09493456780910492, "max": 0.6095234155654907, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 141.62991333007812, "min": -22.7842960357666, "max": 171.88560485839844, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.012951740995049477, "min": -0.016867144033312798, "max": 0.7163528203964233, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.535825252532959, "min": -4.334856033325195, "max": 169.77561950683594, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07004135242196141, "min": 0.0653743783903857, "max": 0.07533266253287965, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0506202863294212, "min": 0.5273286377301576, "max": 1.0506202863294212, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01263396410747839, "min": 9.636882772137009e-05, "max": 0.02646946866353948, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18950946161217586, "min": 0.0012527947603778113, "max": 0.21813815832138064, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.2530497493920002e-05, "min": 1.2530497493920002e-05, "max": 0.0004919177159021714, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00018795746240880004, "min": 0.00018795746240880004, "max": 0.0054318632136274, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250608000000001, "min": 0.10250608000000001, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5375912000000003, "min": 1.3886848, "max": 2.4021923, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026035739200000013, "min": 0.00026035739200000013, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003905360880000002, "min": 0.003905360880000002, "max": 0.10865862274, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013718772679567337, "min": 0.013560573570430279, "max": 0.7486427426338196, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.20578159391880035, "min": 0.18984803557395935, "max": 5.240499019622803, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 367.4268292682927, "min": 331.1770833333333, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30129.0, "min": 15984.0, "max": 33115.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5349877885565526, "min": -1.0000000521540642, "max": 1.6066624844291557, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 125.8689986616373, "min": -30.998001635074615, "max": 154.23959850519896, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5349877885565526, "min": -1.0000000521540642, "max": 1.6066624844291557, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 125.8689986616373, "min": -30.998001635074615, "max": 154.23959850519896, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05257577320919997, "min": 0.04896622308332575, "max": 17.227806771174073, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.311213403154397, "min": 4.015230292832712, "max": 275.64490833878517, "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": "1698327459", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1698330789" }, "total": 3330.0713599460005, "count": 1, "self": 0.730887654000071, "children": { "run_training.setup": { "total": 0.11232093000012355, "count": 1, "self": 0.11232093000012355 }, "TrainerController.start_learning": { "total": 3329.228151362, "count": 1, "self": 2.420279249974101, "children": { "TrainerController._reset_env": { "total": 1.987025678000009, "count": 1, "self": 1.987025678000009 }, "TrainerController.advance": { "total": 3324.7278526370264, "count": 63805, "self": 2.632191798972599, "children": { "env_step": { "total": 2206.1333625310585, "count": 63805, "self": 2041.458903610103, "children": { "SubprocessEnvManager._take_step": { "total": 163.0890063789518, "count": 63805, "self": 6.952099371946588, "children": { "TorchPolicy.evaluate": { "total": 156.13690700700522, "count": 62579, "self": 156.13690700700522 } } }, "workers": { "total": 1.5854525420036225, "count": 63805, "self": 0.0, "children": { "worker_root": { "total": 3322.96563777103, "count": 63805, "is_parallel": true, "self": 1464.0563669940202, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003540024999892921, "count": 1, "is_parallel": true, "self": 0.0012929990000429825, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022470259998499387, "count": 8, "is_parallel": true, "self": 0.0022470259998499387 } } }, "UnityEnvironment.step": { "total": 0.07832962099996621, "count": 1, "is_parallel": true, "self": 0.0007078809999256919, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005827570000747073, "count": 1, "is_parallel": true, "self": 0.0005827570000747073 }, "communicator.exchange": { "total": 0.07490801899984945, "count": 1, "is_parallel": true, "self": 0.07490801899984945 }, "steps_from_proto": { "total": 0.0021309640001163643, "count": 1, "is_parallel": true, "self": 0.0004978520000804565, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016331120000359078, "count": 8, "is_parallel": true, "self": 0.0016331120000359078 } } } } } } }, "UnityEnvironment.step": { "total": 1858.9092707770096, "count": 63804, "is_parallel": true, "self": 47.58919949888036, "children": { "UnityEnvironment._generate_step_input": { "total": 28.27381189295579, "count": 63804, "is_parallel": true, "self": 28.27381189295579 }, "communicator.exchange": { "total": 1650.2045698570853, "count": 63804, "is_parallel": true, "self": 1650.2045698570853 }, "steps_from_proto": { "total": 132.84168952808818, "count": 63804, "is_parallel": true, "self": 28.738861028020892, "children": { "_process_rank_one_or_two_observation": { "total": 104.10282850006729, "count": 510432, "is_parallel": true, "self": 104.10282850006729 } } } } } } } } } } }, "trainer_advance": { "total": 1115.9622983069953, "count": 63805, "self": 5.105888977979021, "children": { "process_trajectory": { "total": 167.34122813901354, "count": 63805, "self": 167.14745671701417, "children": { "RLTrainer._checkpoint": { "total": 0.19377142199937225, "count": 2, "self": 0.19377142199937225 } } }, "_update_policy": { "total": 943.5151811900027, "count": 447, "self": 382.9610483889255, "children": { "TorchPPOOptimizer.update": { "total": 560.5541328010772, "count": 22761, "self": 560.5541328010772 } } } } } } }, "trainer_threads": { "total": 1.140999302151613e-06, "count": 1, "self": 1.140999302151613e-06 }, "TrainerController._save_models": { "total": 0.0929926560002059, "count": 1, "self": 0.0017081530004361412, "children": { "RLTrainer._checkpoint": { "total": 0.09128450299976976, "count": 1, "self": 0.09128450299976976 } } } } } } }