{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4988962709903717, "min": 0.4842311143875122, "max": 1.5239211320877075, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15102.587890625, "min": 14472.69921875, "max": 46229.671875, "count": 33 }, "Pyramids.Step.mean": { "value": 989983.0, "min": 29952.0, "max": 989983.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989983.0, "min": 29952.0, "max": 989983.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3789844214916229, "min": -0.09851595014333725, "max": 0.3789844214916229, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 101.1888427734375, "min": -23.74234390258789, "max": 101.1888427734375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0019585019908845425, "min": -0.02131822519004345, "max": 0.16668298840522766, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.5229200124740601, "min": -5.414829254150391, "max": 40.17060089111328, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06870868112725605, "min": 0.06507219319575511, "max": 0.07286532923474213, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9619215357815847, "min": 0.5003567226207681, "max": 1.092979938521132, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01595828514733252, "min": 0.00047206482112606917, "max": 0.01652654556074959, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22341599206265528, "min": 0.00566477785351283, "max": 0.23137163785049425, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.559390337378568e-06, "min": 7.559390337378568e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010583146472329995, "min": 0.00010583146472329995, "max": 0.003330042089986, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251976428571428, "min": 0.10251976428571428, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4352767, "min": 1.3886848, "max": 2.4823446, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000261724452142857, "min": 0.000261724452142857, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036641423299999987, "min": 0.0036641423299999987, "max": 0.1110103986, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006623172201216221, "min": 0.006542367860674858, "max": 0.3466138541698456, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09272441267967224, "min": 0.09210232645273209, "max": 2.4262969493865967, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 421.8333333333333, "min": 421.8333333333333, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30372.0, "min": 15984.0, "max": 33117.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3836610881197784, "min": -1.0000000521540642, "max": 1.3836610881197784, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 99.62359834462404, "min": -29.920001707971096, "max": 99.62359834462404, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3836610881197784, "min": -1.0000000521540642, "max": 1.3836610881197784, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 99.62359834462404, "min": -29.920001707971096, "max": 99.62359834462404, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.029112515942769177, "min": 0.029112515942769177, "max": 6.904646463692188, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.0961011478793807, "min": 1.9738296375144273, "max": 110.47434341907501, "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": "1692102168", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1692104482" }, "total": 2313.5463765619998, "count": 1, "self": 0.44185051999966163, "children": { "run_training.setup": { "total": 0.04181121100009477, "count": 1, "self": 0.04181121100009477 }, "TrainerController.start_learning": { "total": 2313.062714831, "count": 1, "self": 1.552757860962629, "children": { "TrainerController._reset_env": { "total": 4.012430406000021, "count": 1, "self": 4.012430406000021 }, "TrainerController.advance": { "total": 2307.3964202000375, "count": 63586, "self": 1.5869655660117132, "children": { "env_step": { "total": 1627.2356088909364, "count": 63586, "self": 1507.6863135339859, "children": { "SubprocessEnvManager._take_step": { "total": 118.646486737965, "count": 63586, "self": 5.014347145074225, "children": { "TorchPolicy.evaluate": { "total": 113.63213959289078, "count": 62563, "self": 113.63213959289078 } } }, "workers": { "total": 0.9028086189855458, "count": 63586, "self": 0.0, "children": { "worker_root": { "total": 2307.535342305893, "count": 63586, "is_parallel": true, "self": 925.1778043199424, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018853329997909896, "count": 1, "is_parallel": true, "self": 0.0006062600004952401, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012790729992957495, "count": 8, "is_parallel": true, "self": 0.0012790729992957495 } } }, "UnityEnvironment.step": { "total": 0.047222458999840455, "count": 1, "is_parallel": true, "self": 0.0005680700000993966, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005193359997974767, "count": 1, "is_parallel": true, "self": 0.0005193359997974767 }, "communicator.exchange": { "total": 0.04422560300008627, "count": 1, "is_parallel": true, "self": 0.04422560300008627 }, "steps_from_proto": { "total": 0.0019094499998573156, "count": 1, "is_parallel": true, "self": 0.00039158400022643036, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015178659996308852, "count": 8, "is_parallel": true, "self": 0.0015178659996308852 } } } } } } }, "UnityEnvironment.step": { "total": 1382.3575379859508, "count": 63585, "is_parallel": true, "self": 35.5598175820478, "children": { "UnityEnvironment._generate_step_input": { "total": 24.52261731090448, "count": 63585, "is_parallel": true, "self": 24.52261731090448 }, "communicator.exchange": { "total": 1208.3105884679758, "count": 63585, "is_parallel": true, "self": 1208.3105884679758 }, "steps_from_proto": { "total": 113.96451462502273, "count": 63585, "is_parallel": true, "self": 22.901600431024235, "children": { "_process_rank_one_or_two_observation": { "total": 91.0629141939985, "count": 508680, "is_parallel": true, "self": 91.0629141939985 } } } } } } } } } } }, "trainer_advance": { "total": 678.5738457430894, "count": 63586, "self": 2.81133613205202, "children": { "process_trajectory": { "total": 117.57041418004428, "count": 63586, "self": 117.35379738804431, "children": { "RLTrainer._checkpoint": { "total": 0.21661679199996797, "count": 2, "self": 0.21661679199996797 } } }, "_update_policy": { "total": 558.192095430993, "count": 448, "self": 363.5118055739472, "children": { "TorchPPOOptimizer.update": { "total": 194.68028985704586, "count": 22860, "self": 194.68028985704586 } } } } } } }, "trainer_threads": { "total": 8.719998731976375e-07, "count": 1, "self": 8.719998731976375e-07 }, "TrainerController._save_models": { "total": 0.10110549199998786, "count": 1, "self": 0.0020463649998418987, "children": { "RLTrainer._checkpoint": { "total": 0.09905912700014596, "count": 1, "self": 0.09905912700014596 } } } } } } }