{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.36411893367767334, "min": 0.347688764333725, "max": 1.434644103050232, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10818.7021484375, "min": 10441.7890625, "max": 43521.36328125, "count": 33 }, "Pyramids.Step.mean": { "value": 989970.0, "min": 29952.0, "max": 989970.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989970.0, "min": 29952.0, "max": 989970.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6657077074050903, "min": -0.07704223692417145, "max": 0.6657077074050903, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 192.3895263671875, "min": -18.490137100219727, "max": 192.3895263671875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.061358481645584106, "min": -0.004013091325759888, "max": 0.1963900625705719, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 17.732601165771484, "min": -1.083534598350525, "max": 47.33000564575195, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0680326780627435, "min": 0.06570963778780302, "max": 0.07235078659141436, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0204901709411525, "min": 0.4995702086919758, "max": 1.0852617988712154, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016334848307491094, "min": 0.001317103557566168, "max": 0.016554153625163184, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24502272461236643, "min": 0.011689779240457249, "max": 0.24502272461236643, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.507477497540004e-06, "min": 7.507477497540004e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011261216246310006, "min": 0.00011261216246310006, "max": 0.0036358201880599995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250246, "min": 0.10250246, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5375369, "min": 1.3886848, "max": 2.6119399999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002599957540000002, "min": 0.0002599957540000002, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038999363100000028, "min": 0.0038999363100000028, "max": 0.12121280599999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009498043917119503, "min": 0.009498043917119503, "max": 0.37360522150993347, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14247065782546997, "min": 0.13809536397457123, "max": 2.615236520767212, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 275.60377358490564, "min": 275.60377358490564, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29214.0, "min": 15984.0, "max": 34274.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6713028448678198, "min": -1.0000000521540642, "max": 1.6900277024153436, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 175.48679871112108, "min": -30.534001648426056, "max": 175.48679871112108, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6713028448678198, "min": -1.0000000521540642, "max": 1.6900277024153436, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 175.48679871112108, "min": -30.534001648426056, "max": 175.48679871112108, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.026794836364154306, "min": 0.026794836364154306, "max": 7.6457915138453245, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.813457818236202, "min": 2.813457818236202, "max": 122.33266422152519, "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": "1695402189", "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": "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": "1695404575" }, "total": 2385.3036532669994, "count": 1, "self": 0.5815064260004874, "children": { "run_training.setup": { "total": 0.03940594199957559, "count": 1, "self": 0.03940594199957559 }, "TrainerController.start_learning": { "total": 2384.6827408989993, "count": 1, "self": 1.4771219160647888, "children": { "TrainerController._reset_env": { "total": 3.9737865759998385, "count": 1, "self": 3.9737865759998385 }, "TrainerController.advance": { "total": 2379.131911624934, "count": 64166, "self": 1.5101090560656303, "children": { "env_step": { "total": 1708.088338063846, "count": 64166, "self": 1591.8568740950595, "children": { "SubprocessEnvManager._take_step": { "total": 115.3685499618241, "count": 64166, "self": 5.039768438806277, "children": { "TorchPolicy.evaluate": { "total": 110.32878152301782, "count": 62566, "self": 110.32878152301782 } } }, "workers": { "total": 0.8629140069624555, "count": 64166, "self": 0.0, "children": { "worker_root": { "total": 2378.985732706218, "count": 64166, "is_parallel": true, "self": 910.4156223261634, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002028414999585948, "count": 1, "is_parallel": true, "self": 0.0006310759999905713, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013973389995953767, "count": 8, "is_parallel": true, "self": 0.0013973389995953767 } } }, "UnityEnvironment.step": { "total": 0.05440728299981856, "count": 1, "is_parallel": true, "self": 0.0005948779999016551, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000477920999401249, "count": 1, "is_parallel": true, "self": 0.000477920999401249 }, "communicator.exchange": { "total": 0.05029380599989963, "count": 1, "is_parallel": true, "self": 0.05029380599989963 }, "steps_from_proto": { "total": 0.003040678000616026, "count": 1, "is_parallel": true, "self": 0.0004284819988242816, "children": { "_process_rank_one_or_two_observation": { "total": 0.0026121960017917445, "count": 8, "is_parallel": true, "self": 0.0026121960017917445 } } } } } } }, "UnityEnvironment.step": { "total": 1468.5701103800548, "count": 64165, "is_parallel": true, "self": 34.89470621586588, "children": { "UnityEnvironment._generate_step_input": { "total": 24.23191262713226, "count": 64165, "is_parallel": true, "self": 24.23191262713226 }, "communicator.exchange": { "total": 1296.3889458991998, "count": 64165, "is_parallel": true, "self": 1296.3889458991998 }, "steps_from_proto": { "total": 113.05454563785679, "count": 64165, "is_parallel": true, "self": 22.421051619830905, "children": { "_process_rank_one_or_two_observation": { "total": 90.63349401802589, "count": 513320, "is_parallel": true, "self": 90.63349401802589 } } } } } } } } } } }, "trainer_advance": { "total": 669.5334645050225, "count": 64166, "self": 2.8007377343710687, "children": { "process_trajectory": { "total": 119.32672937566349, "count": 64166, "self": 119.10598056366325, "children": { "RLTrainer._checkpoint": { "total": 0.2207488120002381, "count": 2, "self": 0.2207488120002381 } } }, "_update_policy": { "total": 547.4059973949879, "count": 454, "self": 356.3122683948932, "children": { "TorchPPOOptimizer.update": { "total": 191.09372900009475, "count": 22812, "self": 191.09372900009475 } } } } } } }, "trainer_threads": { "total": 9.440009307581931e-07, "count": 1, "self": 9.440009307581931e-07 }, "TrainerController._save_models": { "total": 0.09991983799955051, "count": 1, "self": 0.001401557999997749, "children": { "RLTrainer._checkpoint": { "total": 0.09851827999955276, "count": 1, "self": 0.09851827999955276 } } } } } } }