{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.500122606754303, "min": 0.4848885238170624, "max": 1.4408429861068726, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14963.66796875, "min": 14639.75390625, "max": 43709.4140625, "count": 33 }, "Pyramids.Step.mean": { "value": 989994.0, "min": 29952.0, "max": 989994.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989994.0, "min": 29952.0, "max": 989994.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5206454992294312, "min": -0.12462763488292694, "max": 0.5394735336303711, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 143.17750549316406, "min": -29.910633087158203, "max": 149.97364807128906, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03783247247338295, "min": -0.10501954704523087, "max": 0.5302673578262329, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 10.403929710388184, "min": -27.725160598754883, "max": 125.6733627319336, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07023699670075895, "min": 0.06597248561785717, "max": 0.07425791147823158, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9833179538106253, "min": 0.519805380347621, "max": 1.027950287486116, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014703587894891264, "min": 0.0004279264805194013, "max": 0.014822875262845108, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2058502305284777, "min": 0.005135117766232816, "max": 0.2075202536798315, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.729275995035713e-06, "min": 7.729275995035713e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010820986393049997, "min": 0.00010820986393049997, "max": 0.003507384230872, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10257639285714289, "min": 0.10257639285714289, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4360695000000003, "min": 1.3886848, "max": 2.569127999999999, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026738164642857134, "min": 0.00026738164642857134, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037433430499999986, "min": 0.0037433430499999986, "max": 0.1169358872, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013480921275913715, "min": 0.013480921275913715, "max": 0.4635303318500519, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18873289227485657, "min": 0.18873289227485657, "max": 3.2447123527526855, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 381.78205128205127, "min": 345.87951807228916, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29779.0, "min": 15984.0, "max": 33329.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.541266640409445, "min": -1.0000000521540642, "max": 1.60591082292867, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 120.21879795193672, "min": -31.9980016797781, "max": 133.57919857650995, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.541266640409445, "min": -1.0000000521540642, "max": 1.60591082292867, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 120.21879795193672, "min": -31.9980016797781, "max": 133.57919857650995, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05351740965274169, "min": 0.05351740965274169, "max": 9.564930640161037, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.1743579529138515, "min": 4.1743579529138515, "max": 153.0388902425766, "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": "1694296347", "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": "1694298621" }, "total": 2274.348290792, "count": 1, "self": 0.49709009000025617, "children": { "run_training.setup": { "total": 0.062165718999949604, "count": 1, "self": 0.062165718999949604 }, "TrainerController.start_learning": { "total": 2273.789034983, "count": 1, "self": 1.5149559179499192, "children": { "TrainerController._reset_env": { "total": 4.972383053000044, "count": 1, "self": 4.972383053000044 }, "TrainerController.advance": { "total": 2267.20618570805, "count": 63639, "self": 1.5485799810394383, "children": { "env_step": { "total": 1605.2746480809813, "count": 63639, "self": 1487.4982249670254, "children": { "SubprocessEnvManager._take_step": { "total": 116.86747741898046, "count": 63639, "self": 4.984044039062724, "children": { "TorchPolicy.evaluate": { "total": 111.88343337991773, "count": 62570, "self": 111.88343337991773 } } }, "workers": { "total": 0.9089456949753867, "count": 63639, "self": 0.0, "children": { "worker_root": { "total": 2268.448401233021, "count": 63639, "is_parallel": true, "self": 904.1653022669996, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.011536839999962467, "count": 1, "is_parallel": true, "self": 0.004451113999721201, "children": { "_process_rank_one_or_two_observation": { "total": 0.007085726000241266, "count": 8, "is_parallel": true, "self": 0.007085726000241266 } } }, "UnityEnvironment.step": { "total": 0.05011343499995746, "count": 1, "is_parallel": true, "self": 0.0005713739999464451, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005243509999672824, "count": 1, "is_parallel": true, "self": 0.0005243509999672824 }, "communicator.exchange": { "total": 0.04623542000001635, "count": 1, "is_parallel": true, "self": 0.04623542000001635 }, "steps_from_proto": { "total": 0.0027822900000273876, "count": 1, "is_parallel": true, "self": 0.00040830300008565246, "children": { "_process_rank_one_or_two_observation": { "total": 0.002373986999941735, "count": 8, "is_parallel": true, "self": 0.002373986999941735 } } } } } } }, "UnityEnvironment.step": { "total": 1364.2830989660213, "count": 63638, "is_parallel": true, "self": 35.5208518650129, "children": { "UnityEnvironment._generate_step_input": { "total": 24.45025613105952, "count": 63638, "is_parallel": true, "self": 24.45025613105952 }, "communicator.exchange": { "total": 1191.1577530969682, "count": 63638, "is_parallel": true, "self": 1191.1577530969682 }, "steps_from_proto": { "total": 113.15423787298073, "count": 63638, "is_parallel": true, "self": 22.64952178791293, "children": { "_process_rank_one_or_two_observation": { "total": 90.5047160850678, "count": 509104, "is_parallel": true, "self": 90.5047160850678 } } } } } } } } } } }, "trainer_advance": { "total": 660.3829576460292, "count": 63639, "self": 2.6960527350526036, "children": { "process_trajectory": { "total": 116.18525806197658, "count": 63639, "self": 115.97030958397681, "children": { "RLTrainer._checkpoint": { "total": 0.21494847799976924, "count": 2, "self": 0.21494847799976924 } } }, "_update_policy": { "total": 541.501646849, "count": 450, "self": 351.28739255399637, "children": { "TorchPPOOptimizer.update": { "total": 190.21425429500368, "count": 22812, "self": 190.21425429500368 } } } } } } }, "trainer_threads": { "total": 8.840002010401804e-07, "count": 1, "self": 8.840002010401804e-07 }, "TrainerController._save_models": { "total": 0.09550941999987117, "count": 1, "self": 0.0015049969997562584, "children": { "RLTrainer._checkpoint": { "total": 0.09400442300011491, "count": 1, "self": 0.09400442300011491 } } } } } } }