{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.7019164562225342, "min": 0.7007043957710266, "max": 1.4973646402359009, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 21068.724609375, "min": 20942.65234375, "max": 45424.0546875, "count": 33 }, "Pyramids.Step.mean": { "value": 989954.0, "min": 29952.0, "max": 989954.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989954.0, "min": 29952.0, "max": 989954.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.15095533430576324, "min": -0.10514713823795319, "max": 0.1956789791584015, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 38.19169998168945, "min": -25.235313415527344, "max": 49.50678253173828, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.07304058223962784, "min": -0.07304058223962784, "max": 0.24906304478645325, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -18.479267120361328, "min": -18.479267120361328, "max": 59.77513122558594, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06655306523781222, "min": 0.06494119721281513, "max": 0.0742110517710614, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9317429133293712, "min": 0.47533356141996164, "max": 1.028908298514651, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013214546504311612, "min": 7.110025983041059e-05, "max": 0.013214546504311612, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18500365106036257, "min": 0.0009954036376257482, "max": 0.18500365106036257, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.5885974705e-06, "min": 7.5885974705e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010624036458700001, "min": 0.00010624036458700001, "max": 0.0027885624704793, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252950000000004, "min": 0.10252950000000004, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4354130000000005, "min": 1.3691136000000002, "max": 2.3168612, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026269705000000007, "min": 0.00026269705000000007, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036777587000000013, "min": 0.0036777587000000013, "max": 0.09298911792999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008422628976404667, "min": 0.008422628976404667, "max": 0.35162821412086487, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11791680753231049, "min": 0.11791680753231049, "max": 2.461397409439087, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 638.9777777777778, "min": 613.125, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28754.0, "min": 15984.0, "max": 32522.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.8332608257946761, "min": -1.0000000521540642, "max": 0.845024970980982, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 38.3299979865551, "min": -32.000001668930054, "max": 40.561198607087135, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.8332608257946761, "min": -1.0000000521540642, "max": 0.845024970980982, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 38.3299979865551, "min": -32.000001668930054, "max": 40.561198607087135, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05807812129521905, "min": 0.05409727368896711, "max": 7.775267387740314, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.671593579580076, "min": 2.596669137070421, "max": 124.40427820384502, "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": "1689958969", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "1689961084" }, "total": 2115.219483479, "count": 1, "self": 1.2521167709996917, "children": { "run_training.setup": { "total": 0.05503485400004138, "count": 1, "self": 0.05503485400004138 }, "TrainerController.start_learning": { "total": 2113.912331854, "count": 1, "self": 1.375856939046571, "children": { "TrainerController._reset_env": { "total": 4.499772394000047, "count": 1, "self": 4.499772394000047 }, "TrainerController.advance": { "total": 2107.8912028789537, "count": 63181, "self": 1.354942348986242, "children": { "env_step": { "total": 1457.6346306129865, "count": 63181, "self": 1350.2079278560198, "children": { "SubprocessEnvManager._take_step": { "total": 106.63645513193865, "count": 63181, "self": 4.608871080921972, "children": { "TorchPolicy.evaluate": { "total": 102.02758405101667, "count": 62550, "self": 102.02758405101667 } } }, "workers": { "total": 0.790247625028087, "count": 63181, "self": 0.0, "children": { "worker_root": { "total": 2109.0420121570364, "count": 63181, "is_parallel": true, "self": 869.7209644589941, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0026685710001856933, "count": 1, "is_parallel": true, "self": 0.0007399650005481817, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019286059996375116, "count": 8, "is_parallel": true, "self": 0.0019286059996375116 } } }, "UnityEnvironment.step": { "total": 0.04712717400002475, "count": 1, "is_parallel": true, "self": 0.000599532000023828, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004812070001207758, "count": 1, "is_parallel": true, "self": 0.0004812070001207758 }, "communicator.exchange": { "total": 0.04426085399995827, "count": 1, "is_parallel": true, "self": 0.04426085399995827 }, "steps_from_proto": { "total": 0.0017855809999218764, "count": 1, "is_parallel": true, "self": 0.0003631429999586544, "children": { "_process_rank_one_or_two_observation": { "total": 0.001422437999963222, "count": 8, "is_parallel": true, "self": 0.001422437999963222 } } } } } } }, "UnityEnvironment.step": { "total": 1239.3210476980423, "count": 63180, "is_parallel": true, "self": 33.67242315904309, "children": { "UnityEnvironment._generate_step_input": { "total": 22.742233316960665, "count": 63180, "is_parallel": true, "self": 22.742233316960665 }, "communicator.exchange": { "total": 1083.9991458610496, "count": 63180, "is_parallel": true, "self": 1083.9991458610496 }, "steps_from_proto": { "total": 98.90724536098901, "count": 63180, "is_parallel": true, "self": 19.778321850036036, "children": { "_process_rank_one_or_two_observation": { "total": 79.12892351095297, "count": 505440, "is_parallel": true, "self": 79.12892351095297 } } } } } } } } } } }, "trainer_advance": { "total": 648.9016299169809, "count": 63181, "self": 2.2951000949317404, "children": { "process_trajectory": { "total": 106.34519706404785, "count": 63181, "self": 106.08378822504733, "children": { "RLTrainer._checkpoint": { "total": 0.2614088390005236, "count": 2, "self": 0.2614088390005236 } } }, "_update_policy": { "total": 540.2613327580013, "count": 422, "self": 350.4265356009787, "children": { "TorchPPOOptimizer.update": { "total": 189.83479715702265, "count": 22863, "self": 189.83479715702265 } } } } } } }, "trainer_threads": { "total": 1.4019997252034955e-06, "count": 1, "self": 1.4019997252034955e-06 }, "TrainerController._save_models": { "total": 0.14549824000005174, "count": 1, "self": 0.001803526999992755, "children": { "RLTrainer._checkpoint": { "total": 0.14369471300005898, "count": 1, "self": 0.14369471300005898 } } } } } } }