{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.15558169782161713, "min": 0.1472327560186386, "max": 1.4351273775100708, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4640.068359375, "min": 4440.5400390625, "max": 43536.0234375, "count": 100 }, "Pyramids.Step.mean": { "value": 2999890.0, "min": 29999.0, "max": 2999890.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999890.0, "min": 29999.0, "max": 2999890.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.765562117099762, "min": -0.10001370310783386, "max": 0.765562117099762, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 225.07525634765625, "min": -24.20331573486328, "max": 225.07525634765625, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.006237243302166462, "min": -0.008571779355406761, "max": 0.371082603931427, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.833749532699585, "min": -2.3058085441589355, "max": 88.31765747070312, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07195211294608199, "min": 0.06418452211591, "max": 0.07522810055901144, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.007329581245148, "min": 0.4885829520223116, "max": 1.0727810624230187, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014831242285863563, "min": 0.00025144599525025384, "max": 0.016989849534140726, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2076373920020899, "min": 0.0032687979382533, "max": 0.2433097602430886, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4847995050999992e-06, "min": 1.4847995050999992e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.078719307139999e-05, "min": 2.078719307139999e-05, "max": 0.003969052576982499, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10049490000000001, "min": 0.10049490000000001, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4069286, "min": 1.3962282666666668, "max": 2.723017500000001, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.944050999999997e-05, "min": 5.944050999999997e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008321671399999995, "min": 0.0008321671399999995, "max": 0.13230944825, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0050049638375639915, "min": 0.004398328252136707, "max": 0.34621429443359375, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.07006949186325073, "min": 0.06157659366726875, "max": 2.4235000610351562, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 231.66153846153847, "min": 231.66153846153847, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30116.0, "min": 16798.0, "max": 32780.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7683384462044789, "min": -0.9999484395788562, "max": 1.7683384462044789, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 229.88399800658226, "min": -30.998401626944542, "max": 229.88399800658226, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7683384462044789, "min": -0.9999484395788562, "max": 1.7683384462044789, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 229.88399800658226, "min": -30.998401626944542, "max": 229.88399800658226, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.01202009530702176, "min": 0.01202009530702176, "max": 6.632727971848319, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.5626123899128288, "min": 1.3960037025608472, "max": 112.75637552142143, "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": "1750769260", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1750776035" }, "total": 6774.91293902, "count": 1, "self": 0.47630109199963044, "children": { "run_training.setup": { "total": 0.02976313499993921, "count": 1, "self": 0.02976313499993921 }, "TrainerController.start_learning": { "total": 6774.406874793, "count": 1, "self": 3.655272752934252, "children": { "TrainerController._reset_env": { "total": 2.263137302000132, "count": 1, "self": 2.263137302000132 }, "TrainerController.advance": { "total": 6768.399277221065, "count": 193521, "self": 3.9567093240020768, "children": { "env_step": { "total": 4840.817838260982, "count": 193521, "self": 4417.187091156227, "children": { "SubprocessEnvManager._take_step": { "total": 421.40556460703215, "count": 193521, "self": 13.051874900156236, "children": { "TorchPolicy.evaluate": { "total": 408.3536897068759, "count": 187548, "self": 408.3536897068759 } } }, "workers": { "total": 2.2251824977224715, "count": 193521, "self": 0.0, "children": { "worker_root": { "total": 6760.150085565226, "count": 193521, "is_parallel": true, "self": 2663.5029470041827, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001928769999949509, "count": 1, "is_parallel": true, "self": 0.0006637619999310118, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012650080000184971, "count": 8, "is_parallel": true, "self": 0.0012650080000184971 } } }, "UnityEnvironment.step": { "total": 0.051287292999859346, "count": 1, "is_parallel": true, "self": 0.0005711480000627489, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005034250000335305, "count": 1, "is_parallel": true, "self": 0.0005034250000335305 }, "communicator.exchange": { "total": 0.048467296999888276, "count": 1, "is_parallel": true, "self": 0.048467296999888276 }, "steps_from_proto": { "total": 0.0017454229998747905, "count": 1, "is_parallel": true, "self": 0.0003859129994907562, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013595100003840344, "count": 8, "is_parallel": true, "self": 0.0013595100003840344 } } } } } } }, "UnityEnvironment.step": { "total": 4096.647138561043, "count": 193520, "is_parallel": true, "self": 94.08022039295383, "children": { "UnityEnvironment._generate_step_input": { "total": 66.43535728009715, "count": 193520, "is_parallel": true, "self": 66.43535728009715 }, "communicator.exchange": { "total": 3657.4118404110645, "count": 193520, "is_parallel": true, "self": 3657.4118404110645 }, "steps_from_proto": { "total": 278.7197204769277, "count": 193520, "is_parallel": true, "self": 55.6945413097319, "children": { "_process_rank_one_or_two_observation": { "total": 223.0251791671958, "count": 1548160, "is_parallel": true, "self": 223.0251791671958 } } } } } } } } } } }, "trainer_advance": { "total": 1923.6247296360805, "count": 193521, "self": 7.528898271088792, "children": { "process_trajectory": { "total": 369.0966860849949, "count": 193521, "self": 368.57821221399627, "children": { "RLTrainer._checkpoint": { "total": 0.518473870998605, "count": 6, "self": 0.518473870998605 } } }, "_update_policy": { "total": 1546.9991452799968, "count": 1395, "self": 851.702338796903, "children": { "TorchPPOOptimizer.update": { "total": 695.2968064830939, "count": 68367, "self": 695.2968064830939 } } } } } } }, "trainer_threads": { "total": 8.53000528877601e-07, "count": 1, "self": 8.53000528877601e-07 }, "TrainerController._save_models": { "total": 0.0891866639994987, "count": 1, "self": 0.001364555999316508, "children": { "RLTrainer._checkpoint": { "total": 0.0878221080001822, "count": 1, "self": 0.0878221080001822 } } } } } } }