{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.36147454380989075, "min": 0.36147454380989075, "max": 1.4426158666610718, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10797.9677734375, "min": 10797.9677734375, "max": 43763.1953125, "count": 33 }, "Pyramids.Step.mean": { "value": 989916.0, "min": 29952.0, "max": 989916.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989916.0, "min": 29952.0, "max": 989916.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5463314056396484, "min": -0.1288667470216751, "max": 0.5953317284584045, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 151.33380126953125, "min": -31.056884765625, "max": 167.28822326660156, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.013992258347570896, "min": -0.022540627047419548, "max": 0.4190542697906494, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.8758554458618164, "min": -5.928184986114502, "max": 99.31586456298828, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07053164289321838, "min": 0.06631826804507346, "max": 0.07365102852210316, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9874430005050574, "min": 0.47997839247136137, "max": 1.085693704718199, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015366178807328523, "min": 0.00016696135665568584, "max": 0.015366178807328523, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21512650330259933, "min": 0.002170497636523916, "max": 0.21512650330259933, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.603254608471431e-06, "min": 7.603254608471431e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010644556451860003, "min": 0.00010644556451860003, "max": 0.003632786289071299, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253438571428575, "min": 0.10253438571428575, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4354814000000005, "min": 1.3886848, "max": 2.6109287000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002631851328571429, "min": 0.0002631851328571429, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003684591860000001, "min": 0.003684591860000001, "max": 0.12111177713, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009903405793011189, "min": 0.009903405793011189, "max": 0.5683497190475464, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1386476755142212, "min": 0.1386476755142212, "max": 3.9784481525421143, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 335.83516483516485, "min": 305.0561797752809, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30561.0, "min": 15984.0, "max": 32949.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6140673788993254, "min": -1.0000000521540642, "max": 1.7022045302120121, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 148.49419885873795, "min": -28.980001628398895, "max": 149.79399865865707, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6140673788993254, "min": -1.0000000521540642, "max": 1.7022045302120121, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 148.49419885873795, "min": -28.980001628398895, "max": 149.79399865865707, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03470028074756872, "min": 0.03162997418919324, "max": 12.023274028673768, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1924258287763223, "min": 2.7834377286490053, "max": 192.3723844587803, "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": "1681810974", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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 --force", "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": "1681813188" }, "total": 2213.7701709559997, "count": 1, "self": 0.4248948009990272, "children": { "run_training.setup": { "total": 0.1030936469999233, "count": 1, "self": 0.1030936469999233 }, "TrainerController.start_learning": { "total": 2213.2421825080005, "count": 1, "self": 1.4172487690270827, "children": { "TrainerController._reset_env": { "total": 3.648315263999848, "count": 1, "self": 3.648315263999848 }, "TrainerController.advance": { "total": 2208.0882546369726, "count": 63918, "self": 1.531184398907044, "children": { "env_step": { "total": 1595.2468049459626, "count": 63918, "self": 1485.5456798400828, "children": { "SubprocessEnvManager._take_step": { "total": 108.8565487019273, "count": 63918, "self": 4.9230100419795235, "children": { "TorchPolicy.evaluate": { "total": 103.93353865994777, "count": 62550, "self": 103.93353865994777 } } }, "workers": { "total": 0.8445764039524875, "count": 63918, "self": 0.0, "children": { "worker_root": { "total": 2208.035303193981, "count": 63918, "is_parallel": true, "self": 837.3531413149685, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017493459999968763, "count": 1, "is_parallel": true, "self": 0.000580610000042725, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011687359999541513, "count": 8, "is_parallel": true, "self": 0.0011687359999541513 } } }, "UnityEnvironment.step": { "total": 0.048567487000127585, "count": 1, "is_parallel": true, "self": 0.000555790999896999, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004800290000730456, "count": 1, "is_parallel": true, "self": 0.0004800290000730456 }, "communicator.exchange": { "total": 0.04584404199999881, "count": 1, "is_parallel": true, "self": 0.04584404199999881 }, "steps_from_proto": { "total": 0.0016876250001587323, "count": 1, "is_parallel": true, "self": 0.0003722340006788727, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013153909994798596, "count": 8, "is_parallel": true, "self": 0.0013153909994798596 } } } } } } }, "UnityEnvironment.step": { "total": 1370.6821618790123, "count": 63917, "is_parallel": true, "self": 32.67942228108495, "children": { "UnityEnvironment._generate_step_input": { "total": 24.23359790693644, "count": 63917, "is_parallel": true, "self": 24.23359790693644 }, "communicator.exchange": { "total": 1215.238830165986, "count": 63917, "is_parallel": true, "self": 1215.238830165986 }, "steps_from_proto": { "total": 98.53031152500489, "count": 63917, "is_parallel": true, "self": 21.50488541295067, "children": { "_process_rank_one_or_two_observation": { "total": 77.02542611205422, "count": 511336, "is_parallel": true, "self": 77.02542611205422 } } } } } } } } } } }, "trainer_advance": { "total": 611.3102652921027, "count": 63918, "self": 2.644608702061305, "children": { "process_trajectory": { "total": 107.50900305004461, "count": 63918, "self": 107.2543145180448, "children": { "RLTrainer._checkpoint": { "total": 0.2546885319998182, "count": 2, "self": 0.2546885319998182 } } }, "_update_policy": { "total": 501.1566535399968, "count": 455, "self": 321.33220241200956, "children": { "TorchPPOOptimizer.update": { "total": 179.82445112798723, "count": 22770, "self": 179.82445112798723 } } } } } } }, "trainer_threads": { "total": 1.2910004443256184e-06, "count": 1, "self": 1.2910004443256184e-06 }, "TrainerController._save_models": { "total": 0.08836254700054269, "count": 1, "self": 0.001336951000666886, "children": { "RLTrainer._checkpoint": { "total": 0.0870255959998758, "count": 1, "self": 0.0870255959998758 } } } } } } }