{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.16138200461864471, "min": 0.15361294150352478, "max": 1.3788249492645264, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4805.310546875, "min": 4598.36767578125, "max": 41828.03515625, "count": 100 }, "Pyramids.Step.mean": { "value": 2999927.0, "min": 29899.0, "max": 2999927.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999927.0, "min": 29899.0, "max": 2999927.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7915738821029663, "min": -0.21575289964675903, "max": 0.8600931167602539, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 235.09744262695312, "min": -51.13343811035156, "max": 263.171142578125, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.009203523397445679, "min": -0.010924026370048523, "max": 0.46224427223205566, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.7334463596343994, "min": -3.1879029273986816, "max": 109.55189514160156, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06845400046347835, "min": 0.06262469362437037, "max": 0.07451761776676222, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.958356006488697, "min": 0.5216233243673355, "max": 1.091893672882625, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015977201329107873, "min": 0.00026986948155374756, "max": 0.01666934664788524, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22368081860751024, "min": 0.0035083032601987184, "max": 0.23337085307039337, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4669495110499997e-06, "min": 1.4669495110499997e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.0537293154699995e-05, "min": 2.0537293154699995e-05, "max": 0.004011905262698266, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10048895000000001, "min": 0.10048895000000001, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4068453, "min": 1.3962282666666668, "max": 2.7375528999999994, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.8846104999999986e-05, "min": 5.8846104999999986e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008238454699999998, "min": 0.0008238454699999998, "max": 0.13373644316, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0070102340541779995, "min": 0.0070102340541779995, "max": 0.6094204783439636, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09814327955245972, "min": 0.09814327955245972, "max": 4.26594352722168, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 232.10236220472441, "min": 208.62585034013605, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29477.0, "min": 16826.0, "max": 32483.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.735036491519875, "min": -0.9997125510126352, "max": 1.783169102800243, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 218.61459793150425, "min": -31.990801632404327, "max": 259.5399991944432, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.735036491519875, "min": -0.9997125510126352, "max": 1.783169102800243, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 218.61459793150425, "min": -31.990801632404327, "max": 259.5399991944432, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.01734163427930085, "min": 0.01644793654904925, "max": 11.900502757114523, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.185045919191907, "min": 2.185045919191907, "max": 202.30854687094688, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1717533265", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1717540779" }, "total": 7513.8324267709995, "count": 1, "self": 0.481063818999246, "children": { "run_training.setup": { "total": 0.05127542399986851, "count": 1, "self": 0.05127542399986851 }, "TrainerController.start_learning": { "total": 7513.300087528, "count": 1, "self": 4.344441298201673, "children": { "TrainerController._reset_env": { "total": 2.29705445400009, "count": 1, "self": 2.29705445400009 }, "TrainerController.advance": { "total": 7506.574606427799, "count": 195005, "self": 4.559219622864475, "children": { "env_step": { "total": 5559.115163401107, "count": 195005, "self": 5146.037840407925, "children": { "SubprocessEnvManager._take_step": { "total": 410.4382893919378, "count": 195005, "self": 14.614020405244219, "children": { "TorchPolicy.evaluate": { "total": 395.8242689866936, "count": 187543, "self": 395.8242689866936 } } }, "workers": { "total": 2.639033601244364, "count": 195005, "self": 0.0, "children": { "worker_root": { "total": 7496.428331201989, "count": 195005, "is_parallel": true, "self": 2737.4647671631656, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021945080000023154, "count": 1, "is_parallel": true, "self": 0.0007076510003116709, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014868569996906444, "count": 8, "is_parallel": true, "self": 0.0014868569996906444 } } }, "UnityEnvironment.step": { "total": 0.052471475999936956, "count": 1, "is_parallel": true, "self": 0.0007135799999105075, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005330520000370598, "count": 1, "is_parallel": true, "self": 0.0005330520000370598 }, "communicator.exchange": { "total": 0.04945247199998448, "count": 1, "is_parallel": true, "self": 0.04945247199998448 }, "steps_from_proto": { "total": 0.001772372000004907, "count": 1, "is_parallel": true, "self": 0.00037776999988636817, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013946020001185389, "count": 8, "is_parallel": true, "self": 0.0013946020001185389 } } } } } } }, "UnityEnvironment.step": { "total": 4758.963564038823, "count": 195004, "is_parallel": true, "self": 104.25589663243409, "children": { "UnityEnvironment._generate_step_input": { "total": 74.41635028916221, "count": 195004, "is_parallel": true, "self": 74.41635028916221 }, "communicator.exchange": { "total": 4268.412138126955, "count": 195004, "is_parallel": true, "self": 4268.412138126955 }, "steps_from_proto": { "total": 311.8791789902714, "count": 195004, "is_parallel": true, "self": 64.4930299291616, "children": { "_process_rank_one_or_two_observation": { "total": 247.3861490611098, "count": 1560032, "is_parallel": true, "self": 247.3861490611098 } } } } } } } } } } }, "trainer_advance": { "total": 1942.900223403828, "count": 195005, "self": 8.610558539808153, "children": { "process_trajectory": { "total": 409.861800114026, "count": 195005, "self": 409.29116479002755, "children": { "RLTrainer._checkpoint": { "total": 0.570635323998431, "count": 6, "self": 0.570635323998431 } } }, "_update_policy": { "total": 1524.427864749994, "count": 1401, "self": 900.9794533438289, "children": { "TorchPPOOptimizer.update": { "total": 623.448411406165, "count": 68388, "self": 623.448411406165 } } } } } } }, "trainer_threads": { "total": 1.0099993232870474e-06, "count": 1, "self": 1.0099993232870474e-06 }, "TrainerController._save_models": { "total": 0.08398433799993654, "count": 1, "self": 0.001561474999107304, "children": { "RLTrainer._checkpoint": { "total": 0.08242286300082924, "count": 1, "self": 0.08242286300082924 } } } } } } }