{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3178635239601135, "min": 0.3178635239601135, "max": 1.3902498483657837, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9490.1337890625, "min": 9490.1337890625, "max": 42174.62109375, "count": 33 }, "Pyramids.Step.mean": { "value": 989897.0, "min": 29913.0, "max": 989897.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989897.0, "min": 29913.0, "max": 989897.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6187642216682434, "min": -0.12025631219148636, "max": 0.7105451226234436, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 174.49151611328125, "min": -28.861515045166016, "max": 206.7686309814453, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.00654757721349597, "min": -0.00654757721349597, "max": 0.4016879200935364, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.846416711807251, "min": -1.846416711807251, "max": 95.60172271728516, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07195698879964074, "min": 0.06670356073593293, "max": 0.07339130777178245, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0073978431949704, "min": 0.49222126522338305, "max": 1.0793419932791346, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016518491339714576, "min": 0.0008587104912144526, "max": 0.01692770151601594, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23125887875600407, "min": 0.010304525894573431, "max": 0.23698782122422318, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4804046494214334e-06, "min": 7.4804046494214334e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010472566509190006, "min": 0.00010472566509190006, "max": 0.0035077388307537993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249343571428572, "min": 0.10249343571428572, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4349081000000001, "min": 1.3886848, "max": 2.5692462, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000259094227857143, "min": 0.000259094227857143, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036273191900000022, "min": 0.0036273191900000022, "max": 0.11694769538000005, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011967840604484081, "min": 0.011889123357832432, "max": 0.5613910555839539, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16754977405071259, "min": 0.1664477288722992, "max": 3.9297375679016113, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 299.6764705882353, "min": 259.5964912280702, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30567.0, "min": 18502.0, "max": 31952.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6414862592138497, "min": -0.9999724659940292, "max": 1.7323783630723353, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 167.43159843981266, "min": -29.981401674449444, "max": 198.22039784491062, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6414862592138497, "min": -0.9999724659940292, "max": 1.7323783630723353, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 167.43159843981266, "min": -29.981401674449444, "max": 198.22039784491062, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.037175722015615295, "min": 0.0354395536100998, "max": 10.51944540754745, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.7919236455927603, "min": 3.582250896914047, "max": 199.86946274340153, "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": "1689017286", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining --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": "1689019768" }, "total": 2481.3725149069987, "count": 1, "self": 0.4816428399981305, "children": { "run_training.setup": { "total": 0.047176578999824414, "count": 1, "self": 0.047176578999824414 }, "TrainerController.start_learning": { "total": 2480.843695488001, "count": 1, "self": 1.5505748190917075, "children": { "TrainerController._reset_env": { "total": 4.270016161000058, "count": 1, "self": 4.270016161000058 }, "TrainerController.advance": { "total": 2474.919614934908, "count": 64308, "self": 1.5617841406801745, "children": { "env_step": { "total": 1802.3584920381927, "count": 64308, "self": 1679.5739220345395, "children": { "SubprocessEnvManager._take_step": { "total": 121.81685093378837, "count": 64308, "self": 5.27247656160489, "children": { "TorchPolicy.evaluate": { "total": 116.54437437218348, "count": 62575, "self": 116.54437437218348 } } }, "workers": { "total": 0.9677190698648701, "count": 64308, "self": 0.0, "children": { "worker_root": { "total": 2474.877100068974, "count": 64308, "is_parallel": true, "self": 922.8974211140794, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001951485999597935, "count": 1, "is_parallel": true, "self": 0.0006457800000134739, "children": { "_process_rank_one_or_two_observation": { "total": 0.001305705999584461, "count": 8, "is_parallel": true, "self": 0.001305705999584461 } } }, "UnityEnvironment.step": { "total": 0.05190225900059886, "count": 1, "is_parallel": true, "self": 0.0005502450012500049, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005636239993691561, "count": 1, "is_parallel": true, "self": 0.0005636239993691561 }, "communicator.exchange": { "total": 0.04862934199991287, "count": 1, "is_parallel": true, "self": 0.04862934199991287 }, "steps_from_proto": { "total": 0.002159048000066832, "count": 1, "is_parallel": true, "self": 0.0004464999983611051, "children": { "_process_rank_one_or_two_observation": { "total": 0.001712548001705727, "count": 8, "is_parallel": true, "self": 0.001712548001705727 } } } } } } }, "UnityEnvironment.step": { "total": 1551.9796789548946, "count": 64307, "is_parallel": true, "self": 35.76387992301534, "children": { "UnityEnvironment._generate_step_input": { "total": 25.675258725037565, "count": 64307, "is_parallel": true, "self": 25.675258725037565 }, "communicator.exchange": { "total": 1372.038220120996, "count": 64307, "is_parallel": true, "self": 1372.038220120996 }, "steps_from_proto": { "total": 118.50232018584575, "count": 64307, "is_parallel": true, "self": 23.562836632136168, "children": { "_process_rank_one_or_two_observation": { "total": 94.93948355370958, "count": 514456, "is_parallel": true, "self": 94.93948355370958 } } } } } } } } } } }, "trainer_advance": { "total": 670.9993387560353, "count": 64308, "self": 2.9493336270397776, "children": { "process_trajectory": { "total": 121.40653355098038, "count": 64308, "self": 121.18808763198012, "children": { "RLTrainer._checkpoint": { "total": 0.2184459190002599, "count": 2, "self": 0.2184459190002599 } } }, "_update_policy": { "total": 546.6434715780151, "count": 456, "self": 351.05654438613965, "children": { "TorchPPOOptimizer.update": { "total": 195.58692719187547, "count": 22821, "self": 195.58692719187547 } } } } } } }, "trainer_threads": { "total": 1.1280008038738742e-06, "count": 1, "self": 1.1280008038738742e-06 }, "TrainerController._save_models": { "total": 0.10348844500003906, "count": 1, "self": 0.0014441620005527511, "children": { "RLTrainer._checkpoint": { "total": 0.10204428299948631, "count": 1, "self": 0.10204428299948631 } } } } } } }