{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.360578715801239, "min": 0.360578715801239, "max": 1.468069076538086, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10771.20703125, "min": 10771.20703125, "max": 44535.34375, "count": 33 }, "Pyramids.Step.mean": { "value": 989961.0, "min": 29952.0, "max": 989961.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989961.0, "min": 29952.0, "max": 989961.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5598650574684143, "min": -0.19676291942596436, "max": 0.6541990637779236, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 156.76222229003906, "min": -46.6328125, "max": 185.7925262451172, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.011289467103779316, "min": -0.004536532796919346, "max": 0.3736550509929657, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.161050796508789, "min": -1.1658889055252075, "max": 89.67721557617188, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07145801514464742, "min": 0.06564152388341932, "max": 0.07341632298713992, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0004122120250638, "min": 0.510575461510138, "max": 1.0656952074108021, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014710568989920871, "min": 0.000771239985513966, "max": 0.01843986393560911, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2059479658588922, "min": 0.010026119811681557, "max": 0.2581580950985275, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.3508046926214245e-06, "min": 7.3508046926214245e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010291126569669994, "min": 0.00010291126569669994, "max": 0.0036325885891371995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10245023571428571, "min": 0.10245023571428571, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4343033, "min": 1.3886848, "max": 2.6175442999999996, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002547785478571428, "min": 0.0002547785478571428, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003566899669999999, "min": 0.003566899669999999, "max": 0.12110519372000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014601359143853188, "min": 0.014601359143853188, "max": 0.4007905125617981, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.20441903173923492, "min": 0.20441903173923492, "max": 2.8055336475372314, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 327.92391304347825, "min": 301.1734693877551, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30169.0, "min": 15984.0, "max": 32596.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6068347701397927, "min": -1.0000000521540642, "max": 1.6784081514544633, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 147.82879885286093, "min": -30.628001749515533, "max": 164.6503985375166, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6068347701397927, "min": -1.0000000521540642, "max": 1.6784081514544633, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 147.82879885286093, "min": -30.628001749515533, "max": 164.6503985375166, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04982187059795251, "min": 0.04849430431649849, "max": 7.057838655076921, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.583612095011631, "min": 4.583612095011631, "max": 112.92541848123074, "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": "1678846594", "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": "1678848857" }, "total": 2262.63163545, "count": 1, "self": 0.4746320470003411, "children": { "run_training.setup": { "total": 0.11723707600003763, "count": 1, "self": 0.11723707600003763 }, "TrainerController.start_learning": { "total": 2262.0397663269996, "count": 1, "self": 1.5498802130141485, "children": { "TrainerController._reset_env": { "total": 5.74632676300007, "count": 1, "self": 5.74632676300007 }, "TrainerController.advance": { "total": 2254.6491039169855, "count": 64031, "self": 1.6656512050326455, "children": { "env_step": { "total": 1628.362624779945, "count": 64031, "self": 1510.5086602418824, "children": { "SubprocessEnvManager._take_step": { "total": 116.91132996601823, "count": 64031, "self": 5.171159316977082, "children": { "TorchPolicy.evaluate": { "total": 111.74017064904115, "count": 62573, "self": 111.74017064904115 } } }, "workers": { "total": 0.942634572044426, "count": 64031, "self": 0.0, "children": { "worker_root": { "total": 2256.521349377988, "count": 64031, "is_parallel": true, "self": 872.3767364309792, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002018566000060673, "count": 1, "is_parallel": true, "self": 0.0006576529999620107, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013609130000986625, "count": 8, "is_parallel": true, "self": 0.0013609130000986625 } } }, "UnityEnvironment.step": { "total": 0.06041286800018497, "count": 1, "is_parallel": true, "self": 0.0005688400001417904, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005061509998540714, "count": 1, "is_parallel": true, "self": 0.0005061509998540714 }, "communicator.exchange": { "total": 0.05758007600002202, "count": 1, "is_parallel": true, "self": 0.05758007600002202 }, "steps_from_proto": { "total": 0.0017578010001670918, "count": 1, "is_parallel": true, "self": 0.0004253219999554858, "children": { "_process_rank_one_or_two_observation": { "total": 0.001332479000211606, "count": 8, "is_parallel": true, "self": 0.001332479000211606 } } } } } } }, "UnityEnvironment.step": { "total": 1384.1446129470087, "count": 64030, "is_parallel": true, "self": 31.83002621810374, "children": { "UnityEnvironment._generate_step_input": { "total": 24.13571891999254, "count": 64030, "is_parallel": true, "self": 24.13571891999254 }, "communicator.exchange": { "total": 1229.3480306939566, "count": 64030, "is_parallel": true, "self": 1229.3480306939566 }, "steps_from_proto": { "total": 98.83083711495578, "count": 64030, "is_parallel": true, "self": 21.937287657998695, "children": { "_process_rank_one_or_two_observation": { "total": 76.89354945695709, "count": 512240, "is_parallel": true, "self": 76.89354945695709 } } } } } } } } } } }, "trainer_advance": { "total": 624.6208279320081, "count": 64031, "self": 2.852424069007384, "children": { "process_trajectory": { "total": 123.59656502499593, "count": 64031, "self": 123.387784206996, "children": { "RLTrainer._checkpoint": { "total": 0.20878081799992287, "count": 2, "self": 0.20878081799992287 } } }, "_update_policy": { "total": 498.17183883800476, "count": 451, "self": 315.46406643994874, "children": { "TorchPPOOptimizer.update": { "total": 182.70777239805602, "count": 22818, "self": 182.70777239805602 } } } } } } }, "trainer_threads": { "total": 1.2850000530306716e-06, "count": 1, "self": 1.2850000530306716e-06 }, "TrainerController._save_models": { "total": 0.09445414899983007, "count": 1, "self": 0.0013746549998359114, "children": { "RLTrainer._checkpoint": { "total": 0.09307949399999416, "count": 1, "self": 0.09307949399999416 } } } } } } }