{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5439472794532776, "min": 0.5387341380119324, "max": 1.4598780870437622, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16153.05859375, "min": 16049.9677734375, "max": 44286.86328125, "count": 33 }, "Pyramids.Step.mean": { "value": 989987.0, "min": 29952.0, "max": 989987.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989987.0, "min": 29952.0, "max": 989987.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.47965386509895325, "min": -0.125241219997406, "max": 0.5370442867279053, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 129.5065460205078, "min": -30.057891845703125, "max": 146.0760498046875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.009490493685007095, "min": -0.02223842591047287, "max": 0.2066325545310974, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -2.5624332427978516, "min": -6.04885196685791, "max": 49.79844665527344, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06933850301997847, "min": 0.06535296257562788, "max": 0.07303936706323709, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9707390422796985, "min": 0.4855138030165443, "max": 1.024065812380286, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015602201858460571, "min": 0.00010590758737836497, "max": 0.01764486909678326, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.218430826018448, "min": 0.0011649834611620147, "max": 0.24702816735496563, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.295133282607144e-06, "min": 7.295133282607144e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010213186595650002, "min": 0.00010213186595650002, "max": 0.003117554860815099, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10243167857142861, "min": 0.10243167857142861, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4340435000000005, "min": 1.3886848, "max": 2.4005089999999996, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025292468928571435, "min": 0.00025292468928571435, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035409456500000006, "min": 0.0035409456500000006, "max": 0.10393457151, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007058271206915379, "min": 0.006736790295690298, "max": 0.3061252534389496, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09881579875946045, "min": 0.0945109948515892, "max": 2.1428768634796143, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 398.86842105263156, "min": 383.53333333333336, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30314.0, "min": 15984.0, "max": 35079.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.469505235062618, "min": -1.0000000521540642, "max": 1.5583808042415201, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 111.68239786475897, "min": -32.000001668930054, "max": 118.44679871201515, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.469505235062618, "min": -1.0000000521540642, "max": 1.5583808042415201, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 111.68239786475897, "min": -32.000001668930054, "max": 118.44679871201515, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.029275640953097825, "min": 0.026695883357121298, "max": 5.959195447154343, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.2249487124354346, "min": 2.0021912517840974, "max": 95.34712715446949, "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": "1679060449", "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", "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": "1679062642" }, "total": 2193.0872409400004, "count": 1, "self": 0.44508147200076564, "children": { "run_training.setup": { "total": 0.12043211099990003, "count": 1, "self": 0.12043211099990003 }, "TrainerController.start_learning": { "total": 2192.5217273569997, "count": 1, "self": 1.419310653037428, "children": { "TrainerController._reset_env": { "total": 6.084513055000116, "count": 1, "self": 6.084513055000116 }, "TrainerController.advance": { "total": 2184.9247929859616, "count": 63568, "self": 1.4455939169706653, "children": { "env_step": { "total": 1551.4486246130296, "count": 63568, "self": 1438.6775451580584, "children": { "SubprocessEnvManager._take_step": { "total": 111.93169292097309, "count": 63568, "self": 4.697211970989429, "children": { "TorchPolicy.evaluate": { "total": 107.23448094998366, "count": 62562, "self": 107.23448094998366 } } }, "workers": { "total": 0.8393865339980948, "count": 63568, "self": 0.0, "children": { "worker_root": { "total": 2187.480073777951, "count": 63568, "is_parallel": true, "self": 866.2298807908896, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019062760002270807, "count": 1, "is_parallel": true, "self": 0.0005982149996270891, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013080610005999915, "count": 8, "is_parallel": true, "self": 0.0013080610005999915 } } }, "UnityEnvironment.step": { "total": 0.04815826599997308, "count": 1, "is_parallel": true, "self": 0.0005204789999879722, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005067440001766954, "count": 1, "is_parallel": true, "self": 0.0005067440001766954 }, "communicator.exchange": { "total": 0.04301082099982523, "count": 1, "is_parallel": true, "self": 0.04301082099982523 }, "steps_from_proto": { "total": 0.004120221999983187, "count": 1, "is_parallel": true, "self": 0.0003950320005969843, "children": { "_process_rank_one_or_two_observation": { "total": 0.0037251899993862025, "count": 8, "is_parallel": true, "self": 0.0037251899993862025 } } } } } } }, "UnityEnvironment.step": { "total": 1321.2501929870614, "count": 63567, "is_parallel": true, "self": 31.222361043191995, "children": { "UnityEnvironment._generate_step_input": { "total": 22.855015946974163, "count": 63567, "is_parallel": true, "self": 22.855015946974163 }, "communicator.exchange": { "total": 1174.2500869339015, "count": 63567, "is_parallel": true, "self": 1174.2500869339015 }, "steps_from_proto": { "total": 92.92272906299377, "count": 63567, "is_parallel": true, "self": 19.818816703934772, "children": { "_process_rank_one_or_two_observation": { "total": 73.103912359059, "count": 508536, "is_parallel": true, "self": 73.103912359059 } } } } } } } } } } }, "trainer_advance": { "total": 632.0305744559614, "count": 63568, "self": 2.5143604839131513, "children": { "process_trajectory": { "total": 116.70272033204265, "count": 63568, "self": 116.50204957604228, "children": { "RLTrainer._checkpoint": { "total": 0.20067075600036333, "count": 2, "self": 0.20067075600036333 } } }, "_update_policy": { "total": 512.8134936400056, "count": 438, "self": 324.82134601598364, "children": { "TorchPPOOptimizer.update": { "total": 187.99214762402198, "count": 22854, "self": 187.99214762402198 } } } } } } }, "trainer_threads": { "total": 9.63999809755478e-07, "count": 1, "self": 9.63999809755478e-07 }, "TrainerController._save_models": { "total": 0.09310969900070631, "count": 1, "self": 0.0017913890005729627, "children": { "RLTrainer._checkpoint": { "total": 0.09131831000013335, "count": 1, "self": 0.09131831000013335 } } } } } } }