{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3249787986278534, "min": 0.3249787986278534, "max": 1.4734036922454834, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9728.5654296875, "min": 9728.5654296875, "max": 44697.17578125, "count": 33 }, "Pyramids.Step.mean": { "value": 989892.0, "min": 29952.0, "max": 989892.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989892.0, "min": 29952.0, "max": 989892.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.531543493270874, "min": -0.10715872049331665, "max": 0.5899242162704468, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 147.7690887451172, "min": -25.825252532958984, "max": 161.6392364501953, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.008407825604081154, "min": 0.008407825604081154, "max": 0.3344036638736725, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.3373754024505615, "min": 2.3373754024505615, "max": 80.25688171386719, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06685146309862985, "min": 0.06608789483062774, "max": 0.07395248807587136, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0027719464794478, "min": 0.4846187508022734, "max": 1.038298601779388, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015338670779620697, "min": 0.0005453237384422482, "max": 0.015758469652999856, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23008006169431044, "min": 0.007202663079117455, "max": 0.23008006169431044, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.527457490880001e-06, "min": 7.527457490880001e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011291186236320002, "min": 0.00011291186236320002, "max": 0.0033820328726558, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250911999999998, "min": 0.10250911999999998, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5376367999999998, "min": 1.3691136000000002, "max": 2.5273442, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026066108800000006, "min": 0.00026066108800000006, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003909916320000001, "min": 0.003909916320000001, "max": 0.11276168557999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012506629340350628, "min": 0.012506629340350628, "max": 0.5250931978225708, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18759943544864655, "min": 0.1819756031036377, "max": 3.675652503967285, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 359.15294117647056, "min": 330.7176470588235, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30528.0, "min": 15984.0, "max": 31986.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5466988052515422, "min": -1.0000000521540642, "max": 1.6475767261067102, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 131.4693984463811, "min": -32.000001668930054, "max": 141.69159844517708, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5466988052515422, "min": -1.0000000521540642, "max": 1.6475767261067102, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 131.4693984463811, "min": -32.000001668930054, "max": 141.69159844517708, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04621422753189108, "min": 0.04554011650395486, "max": 11.662952432408929, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.928209340210742, "min": 3.916450019340118, "max": 186.60723891854286, "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": "1703619504", "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": "1703621717" }, "total": 2212.5597814480006, "count": 1, "self": 0.7360861520000981, "children": { "run_training.setup": { "total": 0.04596340400007648, "count": 1, "self": 0.04596340400007648 }, "TrainerController.start_learning": { "total": 2211.7777318920002, "count": 1, "self": 1.3062778750886537, "children": { "TrainerController._reset_env": { "total": 2.3100204400000166, "count": 1, "self": 2.3100204400000166 }, "TrainerController.advance": { "total": 2208.024900753912, "count": 63716, "self": 1.3835846619099357, "children": { "env_step": { "total": 1574.2631561120022, "count": 63716, "self": 1447.3439167590109, "children": { "SubprocessEnvManager._take_step": { "total": 126.08165484498204, "count": 63716, "self": 4.556458163937577, "children": { "TorchPolicy.evaluate": { "total": 121.52519668104446, "count": 62560, "self": 121.52519668104446 } } }, "workers": { "total": 0.8375845080092859, "count": 63716, "self": 0.0, "children": { "worker_root": { "total": 2206.6279080550275, "count": 63716, "is_parallel": true, "self": 874.9963211659576, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016688589998921088, "count": 1, "is_parallel": true, "self": 0.000501381000276524, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011674779996155848, "count": 8, "is_parallel": true, "self": 0.0011674779996155848 } } }, "UnityEnvironment.step": { "total": 0.07982599699994353, "count": 1, "is_parallel": true, "self": 0.0005624680002256355, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004644529999495717, "count": 1, "is_parallel": true, "self": 0.0004644529999495717 }, "communicator.exchange": { "total": 0.07701527399990482, "count": 1, "is_parallel": true, "self": 0.07701527399990482 }, "steps_from_proto": { "total": 0.001783801999863499, "count": 1, "is_parallel": true, "self": 0.0003931860001102905, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013906159997532086, "count": 8, "is_parallel": true, "self": 0.0013906159997532086 } } } } } } }, "UnityEnvironment.step": { "total": 1331.63158688907, "count": 63715, "is_parallel": true, "self": 35.15457624722694, "children": { "UnityEnvironment._generate_step_input": { "total": 23.952107945947773, "count": 63715, "is_parallel": true, "self": 23.952107945947773 }, "communicator.exchange": { "total": 1175.765352722876, "count": 63715, "is_parallel": true, "self": 1175.765352722876 }, "steps_from_proto": { "total": 96.75954997301915, "count": 63715, "is_parallel": true, "self": 19.072024804158673, "children": { "_process_rank_one_or_two_observation": { "total": 77.68752516886047, "count": 509720, "is_parallel": true, "self": 77.68752516886047 } } } } } } } } } } }, "trainer_advance": { "total": 632.37815998, "count": 63716, "self": 2.5645244500087756, "children": { "process_trajectory": { "total": 124.06506462499306, "count": 63716, "self": 123.84179723999273, "children": { "RLTrainer._checkpoint": { "total": 0.2232673850003266, "count": 2, "self": 0.2232673850003266 } } }, "_update_policy": { "total": 505.74857090499813, "count": 443, "self": 300.81907631199533, "children": { "TorchPPOOptimizer.update": { "total": 204.9294945930028, "count": 22806, "self": 204.9294945930028 } } } } } } }, "trainer_threads": { "total": 1.2779992175637744e-06, "count": 1, "self": 1.2779992175637744e-06 }, "TrainerController._save_models": { "total": 0.13653154500025266, "count": 1, "self": 0.0021518120001928764, "children": { "RLTrainer._checkpoint": { "total": 0.1343797330000598, "count": 1, "self": 0.1343797330000598 } } } } } } }