{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.42023995518684387, "min": 0.417312353849411, "max": 1.3780100345611572, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12728.2275390625, "min": 12359.123046875, "max": 41803.3125, "count": 33 }, "Pyramids.Step.mean": { "value": 989916.0, "min": 29952.0, "max": 989916.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989916.0, "min": 29952.0, "max": 989916.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.494508296251297, "min": -0.11714667826890945, "max": 0.494508296251297, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 134.50625610351562, "min": -28.232349395751953, "max": 134.50625610351562, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.11991354823112488, "min": -0.11991354823112488, "max": 0.37842684984207153, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -32.616485595703125, "min": -32.616485595703125, "max": 89.68716430664062, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06571847101717831, "min": 0.06571847101717831, "max": 0.07338217595599406, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9200585942404964, "min": 0.5136752316919584, "max": 1.0585702346733716, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.025316577455261557, "min": 9.872927177958787e-05, "max": 0.025316577455261557, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.3544320843736618, "min": 0.0011847512613550545, "max": 0.3544320843736618, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.677033155307145e-06, "min": 7.677033155307145e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010747846417430002, "min": 0.00010747846417430002, "max": 0.0032228863257045995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025589785714286, "min": 0.1025589785714286, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358257000000003, "min": 1.3886848, "max": 2.3591821000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026564195928571434, "min": 0.00026564195928571434, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003718987430000001, "min": 0.003718987430000001, "max": 0.10744211046, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012148609384894371, "min": 0.012148609384894371, "max": 0.577397882938385, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1700805276632309, "min": 0.1700805276632309, "max": 4.04178524017334, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 347.358024691358, "min": 347.358024691358, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28136.0, "min": 15984.0, "max": 33088.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.578538251971757, "min": -1.0000000521540642, "max": 1.578538251971757, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 127.86159840971231, "min": -31.999601677060127, "max": 127.86159840971231, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.578538251971757, "min": -1.0000000521540642, "max": 1.578538251971757, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 127.86159840971231, "min": -31.999601677060127, "max": 127.86159840971231, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.043632295292393986, "min": 0.043632295292393986, "max": 12.205158620607108, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.5342159186839126, "min": 3.5342159186839126, "max": 195.28253792971373, "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": "1707277037", "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 --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1707279226" }, "total": 2188.4617900969997, "count": 1, "self": 0.5463724719998027, "children": { "run_training.setup": { "total": 0.0513900639999747, "count": 1, "self": 0.0513900639999747 }, "TrainerController.start_learning": { "total": 2187.864027561, "count": 1, "self": 1.364189994001208, "children": { "TrainerController._reset_env": { "total": 3.480654238999932, "count": 1, "self": 3.480654238999932 }, "TrainerController.advance": { "total": 2182.9293550039993, "count": 63501, "self": 1.4648795259768121, "children": { "env_step": { "total": 1562.4504229729687, "count": 63501, "self": 1426.6441298939899, "children": { "SubprocessEnvManager._take_step": { "total": 134.96270886198624, "count": 63501, "self": 4.798783017974301, "children": { "TorchPolicy.evaluate": { "total": 130.16392584401194, "count": 62557, "self": 130.16392584401194 } } }, "workers": { "total": 0.8435842169925536, "count": 63501, "self": 0.0, "children": { "worker_root": { "total": 2182.709240264026, "count": 63501, "is_parallel": true, "self": 873.9776969380409, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005504161999965618, "count": 1, "is_parallel": true, "self": 0.003926568999986557, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015775929999790606, "count": 8, "is_parallel": true, "self": 0.0015775929999790606 } } }, "UnityEnvironment.step": { "total": 0.09534597100002884, "count": 1, "is_parallel": true, "self": 0.00064071400015564, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005290459999969244, "count": 1, "is_parallel": true, "self": 0.0005290459999969244 }, "communicator.exchange": { "total": 0.09241548599993621, "count": 1, "is_parallel": true, "self": 0.09241548599993621 }, "steps_from_proto": { "total": 0.0017607249999400665, "count": 1, "is_parallel": true, "self": 0.000363355999866144, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013973690000739225, "count": 8, "is_parallel": true, "self": 0.0013973690000739225 } } } } } } }, "UnityEnvironment.step": { "total": 1308.731543325985, "count": 63500, "is_parallel": true, "self": 35.86159204892397, "children": { "UnityEnvironment._generate_step_input": { "total": 26.22287820202314, "count": 63500, "is_parallel": true, "self": 26.22287820202314 }, "communicator.exchange": { "total": 1142.1938291900556, "count": 63500, "is_parallel": true, "self": 1142.1938291900556 }, "steps_from_proto": { "total": 104.45324388498238, "count": 63500, "is_parallel": true, "self": 21.048827884020398, "children": { "_process_rank_one_or_two_observation": { "total": 83.40441600096199, "count": 508000, "is_parallel": true, "self": 83.40441600096199 } } } } } } } } } } }, "trainer_advance": { "total": 619.0140525050538, "count": 63501, "self": 2.6065719700758336, "children": { "process_trajectory": { "total": 124.39129896298061, "count": 63501, "self": 123.9897360509807, "children": { "RLTrainer._checkpoint": { "total": 0.40156291199991756, "count": 2, "self": 0.40156291199991756 } } }, "_update_policy": { "total": 492.0161815719973, "count": 438, "self": 286.9514165750154, "children": { "TorchPPOOptimizer.update": { "total": 205.06476499698192, "count": 22851, "self": 205.06476499698192 } } } } } } }, "trainer_threads": { "total": 9.40000063565094e-07, "count": 1, "self": 9.40000063565094e-07 }, "TrainerController._save_models": { "total": 0.08982738399981827, "count": 1, "self": 0.0013223609994383878, "children": { "RLTrainer._checkpoint": { "total": 0.08850502300037988, "count": 1, "self": 0.08850502300037988 } } } } } } }