{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3569077253341675, "min": 0.353641539812088, "max": 1.3381640911102295, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10821.4423828125, "min": 10767.2158203125, "max": 40594.546875, "count": 33 }, "Pyramids.Step.mean": { "value": 989911.0, "min": 29952.0, "max": 989911.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989911.0, "min": 29952.0, "max": 989911.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6040346026420593, "min": -0.0947328582406044, "max": 0.6040346026420593, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 170.94178771972656, "min": -22.735885620117188, "max": 170.94178771972656, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.011338387615978718, "min": -0.011338387615978718, "max": 0.37206146121025085, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -3.208763599395752, "min": -3.208763599395752, "max": 89.29475402832031, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0684448701226973, "min": 0.0647062408044638, "max": 0.07488378697195278, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9582281817177621, "min": 0.49027942328100976, "max": 1.0676154351608336, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01594100260574903, "min": 0.00027356665512712344, "max": 0.017131213958020367, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22317403648048642, "min": 0.002492218989659548, "max": 0.24483982914049796, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.569118905564283e-06, "min": 7.569118905564283e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010596766467789996, "min": 0.00010596766467789996, "max": 0.0033821369726211, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252300714285714, "min": 0.10252300714285714, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4353221, "min": 1.3691136000000002, "max": 2.5273789000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002620484135714285, "min": 0.0002620484135714285, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003668677789999999, "min": 0.003668677789999999, "max": 0.11276515210999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013837912119925022, "min": 0.013404861092567444, "max": 0.4772012233734131, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19373077154159546, "min": 0.1876680552959442, "max": 3.3404085636138916, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 304.60215053763443, "min": 304.60215053763443, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28328.0, "min": 15984.0, "max": 32569.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6523827820695856, "min": -1.0000000521540642, "max": 1.6523827820695856, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 153.67159873247147, "min": -32.000001668930054, "max": 153.67159873247147, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6523827820695856, "min": -1.0000000521540642, "max": 1.6523827820695856, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 153.67159873247147, "min": -32.000001668930054, "max": 153.67159873247147, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.044104576915576406, "min": 0.044104576915576406, "max": 10.104298051446676, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.1017256531486055, "min": 3.976658143365057, "max": 161.66876882314682, "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": "1697340876", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1697343081" }, "total": 2205.594899757, "count": 1, "self": 0.4770632079994357, "children": { "run_training.setup": { "total": 0.05746492700006911, "count": 1, "self": 0.05746492700006911 }, "TrainerController.start_learning": { "total": 2205.0603716220003, "count": 1, "self": 1.481253010038472, "children": { "TrainerController._reset_env": { "total": 7.950015220999944, "count": 1, "self": 7.950015220999944 }, "TrainerController.advance": { "total": 2195.5527977349616, "count": 63720, "self": 1.51203750086961, "children": { "env_step": { "total": 1590.94682393503, "count": 63720, "self": 1459.2588155339736, "children": { "SubprocessEnvManager._take_step": { "total": 130.8028642930151, "count": 63720, "self": 4.877443795023282, "children": { "TorchPolicy.evaluate": { "total": 125.92542049799181, "count": 62556, "self": 125.92542049799181 } } }, "workers": { "total": 0.8851441080413451, "count": 63720, "self": 0.0, "children": { "worker_root": { "total": 2200.3558242529784, "count": 63720, "is_parallel": true, "self": 860.6648115969888, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.009738329000015256, "count": 1, "is_parallel": true, "self": 0.007666976000109571, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020713529999056846, "count": 8, "is_parallel": true, "self": 0.0020713529999056846 } } }, "UnityEnvironment.step": { "total": 0.05150691200003621, "count": 1, "is_parallel": true, "self": 0.0006903010000769427, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005785019999393626, "count": 1, "is_parallel": true, "self": 0.0005785019999393626 }, "communicator.exchange": { "total": 0.04835521199993309, "count": 1, "is_parallel": true, "self": 0.04835521199993309 }, "steps_from_proto": { "total": 0.001882897000086814, "count": 1, "is_parallel": true, "self": 0.00043063300006451755, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014522640000222964, "count": 8, "is_parallel": true, "self": 0.0014522640000222964 } } } } } } }, "UnityEnvironment.step": { "total": 1339.6910126559897, "count": 63719, "is_parallel": true, "self": 35.40073421087436, "children": { "UnityEnvironment._generate_step_input": { "total": 24.159625845027904, "count": 63719, "is_parallel": true, "self": 24.159625845027904 }, "communicator.exchange": { "total": 1181.090253827042, "count": 63719, "is_parallel": true, "self": 1181.090253827042 }, "steps_from_proto": { "total": 99.04039877304535, "count": 63719, "is_parallel": true, "self": 20.356051303040545, "children": { "_process_rank_one_or_two_observation": { "total": 78.68434747000481, "count": 509752, "is_parallel": true, "self": 78.68434747000481 } } } } } } } } } } }, "trainer_advance": { "total": 603.0939362990621, "count": 63720, "self": 2.716116205059734, "children": { "process_trajectory": { "total": 117.26751319999687, "count": 63720, "self": 117.03234854499681, "children": { "RLTrainer._checkpoint": { "total": 0.23516465500006234, "count": 2, "self": 0.23516465500006234 } } }, "_update_policy": { "total": 483.1103068940055, "count": 441, "self": 288.7499267229921, "children": { "TorchPPOOptimizer.update": { "total": 194.3603801710134, "count": 22779, "self": 194.3603801710134 } } } } } } }, "trainer_threads": { "total": 1.1050001376133878e-06, "count": 1, "self": 1.1050001376133878e-06 }, "TrainerController._save_models": { "total": 0.07630455100024847, "count": 1, "self": 0.001465527000164002, "children": { "RLTrainer._checkpoint": { "total": 0.07483902400008446, "count": 1, "self": 0.07483902400008446 } } } } } } }