{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.7286418676376343, "min": 0.6391339898109436, "max": 1.484389066696167, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 21870.9140625, "min": 18989.94921875, "max": 45030.42578125, "count": 33 }, "Pyramids.Step.mean": { "value": 989891.0, "min": 29952.0, "max": 989891.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989891.0, "min": 29952.0, "max": 989891.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.05668890103697777, "min": -0.17862895131111145, "max": 0.09046962112188339, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 13.88878059387207, "min": -42.335060119628906, "max": 22.436466217041016, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.031163666397333145, "min": 0.005397243425250053, "max": 0.37113887071609497, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.635098457336426, "min": 1.3277218341827393, "max": 89.44446563720703, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06320995998666498, "min": 0.06320995998666498, "max": 0.07316363093226842, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.8849394398133097, "min": 0.48649473633281304, "max": 1.0423098736244034, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.005269541817481286, "min": 0.0002284143478532637, "max": 0.008819635463935981, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.073773585444738, "min": 0.002969386522092428, "max": 0.1130588423209024, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.201361885292856e-06, "min": 7.201361885292856e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010081906639409997, "min": 0.00010081906639409997, "max": 0.0035075207308265, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10240042142857143, "min": 0.10240042142857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4336059, "min": 1.3886848, "max": 2.5691735000000007, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002498021007142857, "min": 0.0002498021007142857, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0034972294099999994, "min": 0.0034972294099999994, "max": 0.11694043265000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014499842189252377, "min": 0.014499842189252377, "max": 0.6146382689476013, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.20299778878688812, "min": 0.20299778878688812, "max": 4.3024678230285645, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 814.1714285714286, "min": 766.3809523809524, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28496.0, "min": 15984.0, "max": 33404.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.0426171002643449, "min": -1.0000000521540642, "max": 0.32856662127943265, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 1.4915985092520714, "min": -29.98920153081417, "max": 13.799798093736172, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.0426171002643449, "min": -1.0000000521540642, "max": 0.32856662127943265, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 1.4915985092520714, "min": -29.98920153081417, "max": 13.799798093736172, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.12677596508458788, "min": 0.11418206793245017, "max": 12.908542780205607, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.437158777960576, "min": 4.437158777960576, "max": 206.53668448328972, "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": "1770809144", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1770811337" }, "total": 2192.789102951, "count": 1, "self": 0.5794443009999668, "children": { "run_training.setup": { "total": 0.0334163620000254, "count": 1, "self": 0.0334163620000254 }, "TrainerController.start_learning": { "total": 2192.176242288, "count": 1, "self": 1.4430577250518581, "children": { "TrainerController._reset_env": { "total": 2.111284307999995, "count": 1, "self": 2.111284307999995 }, "TrainerController.advance": { "total": 2188.541236711948, "count": 63272, "self": 1.5544894070135342, "children": { "env_step": { "total": 1532.1147258749527, "count": 63272, "self": 1376.21295500988, "children": { "SubprocessEnvManager._take_step": { "total": 155.06063339904972, "count": 63272, "self": 4.725506347033843, "children": { "TorchPolicy.evaluate": { "total": 150.33512705201588, "count": 62558, "self": 150.33512705201588 } } }, "workers": { "total": 0.8411374660229285, "count": 63272, "self": 0.0, "children": { "worker_root": { "total": 2185.723474282982, "count": 63272, "is_parallel": true, "self": 928.2884564669446, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001871465000021999, "count": 1, "is_parallel": true, "self": 0.00059826200003954, "children": { "_process_rank_one_or_two_observation": { "total": 0.001273202999982459, "count": 8, "is_parallel": true, "self": 0.001273202999982459 } } }, "UnityEnvironment.step": { "total": 0.05526827800008505, "count": 1, "is_parallel": true, "self": 0.0005328290001216374, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005626920001304825, "count": 1, "is_parallel": true, "self": 0.0005626920001304825 }, "communicator.exchange": { "total": 0.052606104999995296, "count": 1, "is_parallel": true, "self": 0.052606104999995296 }, "steps_from_proto": { "total": 0.0015666519998376316, "count": 1, "is_parallel": true, "self": 0.0003440919995227887, "children": { "_process_rank_one_or_two_observation": { "total": 0.001222560000314843, "count": 8, "is_parallel": true, "self": 0.001222560000314843 } } } } } } }, "UnityEnvironment.step": { "total": 1257.4350178160373, "count": 63271, "is_parallel": true, "self": 34.893287354094355, "children": { "UnityEnvironment._generate_step_input": { "total": 23.686142370937205, "count": 63271, "is_parallel": true, "self": 23.686142370937205 }, "communicator.exchange": { "total": 1088.249003496027, "count": 63271, "is_parallel": true, "self": 1088.249003496027 }, "steps_from_proto": { "total": 110.60658459497881, "count": 63271, "is_parallel": true, "self": 23.099915793805394, "children": { "_process_rank_one_or_two_observation": { "total": 87.50666880117342, "count": 506168, "is_parallel": true, "self": 87.50666880117342 } } } } } } } } } } }, "trainer_advance": { "total": 654.8720214299819, "count": 63272, "self": 2.6665097129493915, "children": { "process_trajectory": { "total": 122.5564371890348, "count": 63272, "self": 122.36616655903458, "children": { "RLTrainer._checkpoint": { "total": 0.19027063000021371, "count": 2, "self": 0.19027063000021371 } } }, "_update_policy": { "total": 529.6490745279978, "count": 448, "self": 294.13856702098724, "children": { "TorchPPOOptimizer.update": { "total": 235.51050750701052, "count": 22758, "self": 235.51050750701052 } } } } } } }, "trainer_threads": { "total": 9.180002962239087e-07, "count": 1, "self": 9.180002962239087e-07 }, "TrainerController._save_models": { "total": 0.08066262500005905, "count": 1, "self": 0.001048835000347026, "children": { "RLTrainer._checkpoint": { "total": 0.07961378999971203, "count": 1, "self": 0.07961378999971203 } } } } } } }