{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4552607536315918, "min": 0.4552607536315918, "max": 1.3890786170959473, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13614.1171875, "min": 13614.1171875, "max": 42139.08984375, "count": 33 }, "Pyramids.Step.mean": { "value": 989896.0, "min": 29952.0, "max": 989896.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989896.0, "min": 29952.0, "max": 989896.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4479615390300751, "min": -0.11315439641475677, "max": 0.5596954226493835, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 121.84553527832031, "min": -27.157054901123047, "max": 156.7147216796875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.026580432429909706, "min": 0.0019260324770584702, "max": 0.48887860774993896, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.229877471923828, "min": 0.5238808393478394, "max": 115.86422729492188, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06750063991889224, "min": 0.06598390141593002, "max": 0.07350494109160702, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9450089588644914, "min": 0.5009882428324394, "max": 1.075012046281093, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012933673121941476, "min": 0.0012281882492127575, "max": 0.013644454545491111, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18107142370718066, "min": 0.01473825899055309, "max": 0.20124216485904373, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.303554708371429e-06, "min": 7.303554708371429e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010224976591720001, "min": 0.00010224976591720001, "max": 0.0036085749971417, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10243448571428572, "min": 0.10243448571428572, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4340828, "min": 1.3886848, "max": 2.5028582999999993, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002532051228571429, "min": 0.0002532051228571429, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003544871720000001, "min": 0.003544871720000001, "max": 0.12029554416999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007566539105027914, "min": 0.007566539105027914, "max": 0.553449273109436, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10593155026435852, "min": 0.10593155026435852, "max": 3.8741447925567627, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 399.54794520547944, "min": 359.95, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29167.0, "min": 15984.0, "max": 32796.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3864459276602075, "min": -1.0000000521540642, "max": 1.5666506063145926, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 102.59699864685535, "min": -26.8242017775774, "max": 129.00119849294424, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3864459276602075, "min": -1.0000000521540642, "max": 1.5666506063145926, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 102.59699864685535, "min": -26.8242017775774, "max": 129.00119849294424, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.031014975915093453, "min": 0.031014975915093453, "max": 11.43677225895226, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.2951082177169155, "min": 2.28681590816268, "max": 182.98835614323616, "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": "1703589352", "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": "1703591515" }, "total": 2163.854275922, "count": 1, "self": 0.48880070999985037, "children": { "run_training.setup": { "total": 0.045754596000051606, "count": 1, "self": 0.045754596000051606 }, "TrainerController.start_learning": { "total": 2163.319720616, "count": 1, "self": 1.4376344240381513, "children": { "TrainerController._reset_env": { "total": 1.9868114359999254, "count": 1, "self": 1.9868114359999254 }, "TrainerController.advance": { "total": 2159.809460662962, "count": 63800, "self": 1.492703932909535, "children": { "env_step": { "total": 1538.5501671099873, "count": 63800, "self": 1404.8493390099159, "children": { "SubprocessEnvManager._take_step": { "total": 132.78636688199094, "count": 63800, "self": 4.896948401969212, "children": { "TorchPolicy.evaluate": { "total": 127.88941848002173, "count": 62556, "self": 127.88941848002173 } } }, "workers": { "total": 0.9144612180805325, "count": 63800, "self": 0.0, "children": { "worker_root": { "total": 2158.2304872509517, "count": 63800, "is_parallel": true, "self": 875.4522532019314, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018167489999996178, "count": 1, "is_parallel": true, "self": 0.000571092000200224, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012456569997993938, "count": 8, "is_parallel": true, "self": 0.0012456569997993938 } } }, "UnityEnvironment.step": { "total": 0.051762760999963575, "count": 1, "is_parallel": true, "self": 0.0005842719997417589, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000538468000058856, "count": 1, "is_parallel": true, "self": 0.000538468000058856 }, "communicator.exchange": { "total": 0.04895432500006791, "count": 1, "is_parallel": true, "self": 0.04895432500006791 }, "steps_from_proto": { "total": 0.0016856960000950494, "count": 1, "is_parallel": true, "self": 0.00038805899998806126, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012976370001069881, "count": 8, "is_parallel": true, "self": 0.0012976370001069881 } } } } } } }, "UnityEnvironment.step": { "total": 1282.7782340490203, "count": 63799, "is_parallel": true, "self": 35.7090003870228, "children": { "UnityEnvironment._generate_step_input": { "total": 26.883785628041096, "count": 63799, "is_parallel": true, "self": 26.883785628041096 }, "communicator.exchange": { "total": 1114.955181152962, "count": 63799, "is_parallel": true, "self": 1114.955181152962 }, "steps_from_proto": { "total": 105.23026688099435, "count": 63799, "is_parallel": true, "self": 21.633767917059913, "children": { "_process_rank_one_or_two_observation": { "total": 83.59649896393444, "count": 510392, "is_parallel": true, "self": 83.59649896393444 } } } } } } } } } } }, "trainer_advance": { "total": 619.7665896200651, "count": 63800, "self": 2.788588436953205, "children": { "process_trajectory": { "total": 127.39151183710965, "count": 63800, "self": 127.19829672910964, "children": { "RLTrainer._checkpoint": { "total": 0.19321510800000397, "count": 2, "self": 0.19321510800000397 } } }, "_update_policy": { "total": 489.5864893460023, "count": 455, "self": 289.6388604839792, "children": { "TorchPPOOptimizer.update": { "total": 199.94762886202307, "count": 22821, "self": 199.94762886202307 } } } } } } }, "trainer_threads": { "total": 1.1929996617254801e-06, "count": 1, "self": 1.1929996617254801e-06 }, "TrainerController._save_models": { "total": 0.08581290000029185, "count": 1, "self": 0.0014099420000093232, "children": { "RLTrainer._checkpoint": { "total": 0.08440295800028252, "count": 1, "self": 0.08440295800028252 } } } } } } }