{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 1.1421990394592285, "min": 1.1421990394592285, "max": 1.4469332695007324, "count": 2 }, "Pyramids.Policy.Entropy.sum": { "value": 34211.14453125, "min": 34211.14453125, "max": 43894.16796875, "count": 2 }, "Pyramids.Step.mean": { "value": 59934.0, "min": 29907.0, "max": 59934.0, "count": 2 }, "Pyramids.Step.sum": { "value": 59934.0, "min": 29907.0, "max": 59934.0, "count": 2 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.08758336305618286, "min": -0.1579701453447342, "max": -0.08758336305618286, "count": 2 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -21.107589721679688, "min": -37.43892288208008, "max": -21.107589721679688, "count": 2 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.3425224721431732, "min": 0.3425224721431732, "max": 0.36890387535095215, "count": 2 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 82.54791259765625, "min": 82.54791259765625, "max": 87.43022155761719, "count": 2 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06907772339999176, "min": 0.06907772339999176, "max": 0.07148779887152734, "count": 2 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.7598549573999094, "min": 0.5004145921006914, "max": 0.7598549573999094, "count": 2 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0029509683682251227, "min": 0.0029509683682251227, "max": 0.00923219236376042, "count": 2 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.03246065205047635, "min": 0.03246065205047635, "max": 0.06462534654632293, "count": 2 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00029552526512794243, "min": 0.00029552526512794243, "max": 0.00029838354339596195, "count": 2 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0032507779164073665, "min": 0.0020886848037717336, "max": 0.0032507779164073665, "count": 2 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.19850842121212126, "min": 0.19850842121212126, "max": 0.19946118095238097, "count": 2 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.1835926333333338, "min": 1.3962282666666668, "max": 2.1835926333333338, "count": 2 }, "Pyramids.Policy.Beta.mean": { "value": 0.00985099127909091, "min": 0.00985099127909091, "max": 0.009946171977142856, "count": 2 }, "Pyramids.Policy.Beta.sum": { "value": 0.10836090407000001, "min": 0.06962320384, "max": 0.10836090407000001, "count": 2 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.19209426641464233, "min": 0.19209426641464233, "max": 0.5262088179588318, "count": 2 }, "Pyramids.Losses.RNDLoss.sum": { "value": 2.113036870956421, "min": 2.113036870956421, "max": 3.6834616661071777, "count": 2 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 969.34375, "min": 969.34375, "max": 990.2352941176471, "count": 2 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31019.0, "min": 16834.0, "max": 31019.0, "count": 2 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.8452812964096665, "min": -0.873529464006424, "max": -0.8452812964096665, "count": 2 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -27.04900148510933, "min": -27.04900148510933, "max": -14.850000888109207, "count": 2 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.8452812964096665, "min": -0.873529464006424, "max": -0.8452812964096665, "count": 2 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -27.04900148510933, "min": -27.04900148510933, "max": -14.850000888109207, "count": 2 }, "Pyramids.Policy.RndReward.mean": { "value": 2.680746603757143, "min": 2.680746603757143, "max": 9.921628456781892, "count": 2 }, "Pyramids.Policy.RndReward.sum": { "value": 85.78389132022858, "min": 85.78389132022858, "max": 168.66768376529217, "count": 2 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1687796363", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "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": "1687796557" }, "total": 193.9863496920002, "count": 1, "self": 0.350301766000257, "children": { "run_training.setup": { "total": 0.04735407199996189, "count": 1, "self": 0.04735407199996189 }, "TrainerController.start_learning": { "total": 193.58869385399998, "count": 1, "self": 0.14356919600822948, "children": { "TrainerController._reset_env": { "total": 1.4570415860000594, "count": 1, "self": 1.4570415860000594 }, "TrainerController.advance": { "total": 191.73673356399172, "count": 3898, "self": 0.14451106800152047, "children": { "env_step": { "total": 113.6184350370022, "count": 3898, "self": 103.96310160800726, "children": { "SubprocessEnvManager._take_step": { "total": 9.572066176993758, "count": 3898, "self": 0.509737299007611, "children": { "TorchPolicy.evaluate": { "total": 9.062328877986147, "count": 3896, "self": 9.062328877986147 } } }, "workers": { "total": 0.08326725200117835, "count": 3898, "self": 0.0, "children": { "worker_root": { "total": 192.64975713399735, "count": 3898, "is_parallel": true, "self": 99.61318612699029, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002764651000006779, "count": 1, "is_parallel": true, "self": 0.0009251729995867208, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018394780004200584, "count": 8, "is_parallel": true, "self": 0.0018394780004200584 } } }, "UnityEnvironment.step": { "total": 0.06407348600009755, "count": 1, "is_parallel": true, "self": 0.0008235379998495773, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003729340000973025, "count": 1, "is_parallel": true, "self": 0.0003729340000973025 }, "communicator.exchange": { "total": 0.060339519000081054, "count": 1, "is_parallel": true, "self": 0.060339519000081054 }, "steps_from_proto": { "total": 0.0025374950000696117, "count": 1, "is_parallel": true, "self": 0.0005127160000029107, "children": { "_process_rank_one_or_two_observation": { "total": 0.002024779000066701, "count": 8, "is_parallel": true, "self": 0.002024779000066701 } } } } } } }, "UnityEnvironment.step": { "total": 93.03657100700707, "count": 3897, "is_parallel": true, "self": 2.8727860070187035, "children": { "UnityEnvironment._generate_step_input": { "total": 1.6148803960036275, "count": 3897, "is_parallel": true, "self": 1.6148803960036275 }, "communicator.exchange": { "total": 79.8298176029889, "count": 3897, "is_parallel": true, "self": 79.8298176029889 }, "steps_from_proto": { "total": 8.719087000995842, "count": 3897, "is_parallel": true, "self": 1.884151768025049, "children": { "_process_rank_one_or_two_observation": { "total": 6.834935232970793, "count": 31176, "is_parallel": true, "self": 6.834935232970793 } } } } } } } } } } }, "trainer_advance": { "total": 77.973787458988, "count": 3898, "self": 0.18792251598119947, "children": { "process_trajectory": { "total": 9.529915744006757, "count": 3898, "self": 9.529915744006757 }, "_update_policy": { "total": 68.25594919900004, "count": 19, "self": 28.619619604996842, "children": { "TorchPPOOptimizer.update": { "total": 39.6363295940032, "count": 1404, "self": 39.6363295940032 } } } } } } }, "trainer_threads": { "total": 1.5220000477711437e-06, "count": 1, "self": 1.5220000477711437e-06 }, "TrainerController._save_models": { "total": 0.2513479859999279, "count": 1, "self": 0.0025734299999840005, "children": { "RLTrainer._checkpoint": { "total": 0.2487745559999439, "count": 1, "self": 0.2487745559999439 } } } } } } }