{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3710872530937195, "min": 0.35479119420051575, "max": 1.5143848657608032, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11174.1796875, "min": 10626.7060546875, "max": 45940.37890625, "count": 33 }, "Pyramids.Step.mean": { "value": 989995.0, "min": 29952.0, "max": 989995.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989995.0, "min": 29952.0, "max": 989995.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.557255744934082, "min": -0.14526034891605377, "max": 0.557255744934082, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 157.1461181640625, "min": -34.42670440673828, "max": 157.1461181640625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03877447172999382, "min": -0.006362123414874077, "max": 0.36770954728126526, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 10.934401512145996, "min": -1.7177733182907104, "max": 87.14716339111328, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0672745228661808, "min": 0.06501670798158611, "max": 0.07346477177524312, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9418433201265312, "min": 0.4956838974572622, "max": 1.0732063263179346, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01629458488845945, "min": 0.0006526181452389054, "max": 0.01629458488845945, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22812418843843227, "min": 0.00848403588810577, "max": 0.22812418843843227, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.612726033885715e-06, "min": 7.612726033885715e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010657816447440001, "min": 0.00010657816447440001, "max": 0.0035084789305070995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253754285714287, "min": 0.10253754285714287, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4355256, "min": 1.3886848, "max": 2.5694928999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026350053142857146, "min": 0.00026350053142857146, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00368900744, "min": 0.00368900744, "max": 0.11697234071000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013825265690684319, "min": 0.013825265690684319, "max": 0.38135233521461487, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19355371594429016, "min": 0.19355371594429016, "max": 2.669466257095337, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 334.0113636363636, "min": 334.0113636363636, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29393.0, "min": 15984.0, "max": 33057.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6432522562417118, "min": -1.0000000521540642, "max": 1.6432522562417118, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 144.60619854927063, "min": -30.46620174497366, "max": 144.60619854927063, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6432522562417118, "min": -1.0000000521540642, "max": 1.6432522562417118, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 144.60619854927063, "min": -30.46620174497366, "max": 144.60619854927063, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.047644139063446674, "min": 0.047644139063446674, "max": 7.428159176371992, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.1926842375833075, "min": 4.1926842375833075, "max": 118.85054682195187, "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": "1703515782", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1703517998" }, "total": 2215.7548088470003, "count": 1, "self": 0.4794476430006398, "children": { "run_training.setup": { "total": 0.07070936500008429, "count": 1, "self": 0.07070936500008429 }, "TrainerController.start_learning": { "total": 2215.204651839, "count": 1, "self": 1.359752002966161, "children": { "TrainerController._reset_env": { "total": 2.3331976160000067, "count": 1, "self": 2.3331976160000067 }, "TrainerController.advance": { "total": 2211.4257492580336, "count": 63766, "self": 1.4513701620035135, "children": { "env_step": { "total": 1570.8221303140824, "count": 63766, "self": 1436.3440708690725, "children": { "SubprocessEnvManager._take_step": { "total": 133.61226920101285, "count": 63766, "self": 4.84103026803723, "children": { "TorchPolicy.evaluate": { "total": 128.77123893297562, "count": 62554, "self": 128.77123893297562 } } }, "workers": { "total": 0.8657902439970258, "count": 63766, "self": 0.0, "children": { "worker_root": { "total": 2209.7449179168934, "count": 63766, "is_parallel": true, "self": 896.1744166428964, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017345950000162702, "count": 1, "is_parallel": true, "self": 0.0005544049997752154, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011801900002410548, "count": 8, "is_parallel": true, "self": 0.0011801900002410548 } } }, "UnityEnvironment.step": { "total": 0.05237587900001017, "count": 1, "is_parallel": true, "self": 0.0006416359999548149, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005207960000461753, "count": 1, "is_parallel": true, "self": 0.0005207960000461753 }, "communicator.exchange": { "total": 0.04948841400005222, "count": 1, "is_parallel": true, "self": 0.04948841400005222 }, "steps_from_proto": { "total": 0.0017250329999569658, "count": 1, "is_parallel": true, "self": 0.000370162000081109, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013548709998758568, "count": 8, "is_parallel": true, "self": 0.0013548709998758568 } } } } } } }, "UnityEnvironment.step": { "total": 1313.570501273997, "count": 63765, "is_parallel": true, "self": 34.69091422898123, "children": { "UnityEnvironment._generate_step_input": { "total": 25.305957065010944, "count": 63765, "is_parallel": true, "self": 25.305957065010944 }, "communicator.exchange": { "total": 1152.4164550949642, "count": 63765, "is_parallel": true, "self": 1152.4164550949642 }, "steps_from_proto": { "total": 101.1571748850406, "count": 63765, "is_parallel": true, "self": 20.606153722172394, "children": { "_process_rank_one_or_two_observation": { "total": 80.55102116286821, "count": 510120, "is_parallel": true, "self": 80.55102116286821 } } } } } } } } } } }, "trainer_advance": { "total": 639.152248781948, "count": 63766, "self": 2.610875363061041, "children": { "process_trajectory": { "total": 128.0266002138983, "count": 63766, "self": 127.8289334128981, "children": { "RLTrainer._checkpoint": { "total": 0.19766680100019585, "count": 2, "self": 0.19766680100019585 } } }, "_update_policy": { "total": 508.5147732049886, "count": 450, "self": 305.11276038298047, "children": { "TorchPPOOptimizer.update": { "total": 203.40201282200815, "count": 22803, "self": 203.40201282200815 } } } } } } }, "trainer_threads": { "total": 9.61000296229031e-07, "count": 1, "self": 9.61000296229031e-07 }, "TrainerController._save_models": { "total": 0.08595200099989597, "count": 1, "self": 0.0016194410000025528, "children": { "RLTrainer._checkpoint": { "total": 0.08433255999989342, "count": 1, "self": 0.08433255999989342 } } } } } } }