{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5008999705314636, "min": 0.4773056209087372, "max": 1.4854872226715088, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15123.171875, "min": 14242.7998046875, "max": 45063.7421875, "count": 33 }, "Pyramids.Step.mean": { "value": 989944.0, "min": 29952.0, "max": 989944.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989944.0, "min": 29952.0, "max": 989944.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.24567793309688568, "min": -0.10527270287275314, "max": 0.2654494345188141, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 61.91083908081055, "min": -25.26544952392578, "max": 68.75140380859375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.06088830158114433, "min": -0.019152160733938217, "max": 0.2694939970970154, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 15.343852043151855, "min": -4.768887996673584, "max": 63.87007522583008, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07094593892026892, "min": 0.0651082992406091, "max": 0.07574394675795973, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0641890838040338, "min": 0.5302076273057181, "max": 1.0641890838040338, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.009234968995188669, "min": 0.0005701018202355009, "max": 0.014187979038036782, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.13852453492783004, "min": 0.007981425483297012, "max": 0.19863170653251494, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.5044174985600025e-06, "min": 7.5044174985600025e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011256626247840004, "min": 0.00011256626247840004, "max": 0.0036301444899518994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250144000000001, "min": 0.10250144000000001, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5375216000000003, "min": 1.3886848, "max": 2.6100480999999998, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025989385600000013, "min": 0.00025989385600000013, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003898407840000002, "min": 0.003898407840000002, "max": 0.12102380519, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008191419765353203, "min": 0.007582017220556736, "max": 0.34768661856651306, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12287130206823349, "min": 0.10614824295043945, "max": 2.4338064193725586, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 584.0217391304348, "min": 579.433962264151, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 26865.0, "min": 15984.0, "max": 33031.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.0245390949041948, "min": -1.0000000521540642, "max": 1.0245390949041948, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 47.12879836559296, "min": -28.674001529812813, "max": 51.282198294997215, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.0245390949041948, "min": -1.0000000521540642, "max": 1.0245390949041948, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 47.12879836559296, "min": -28.674001529812813, "max": 51.282198294997215, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.052135885666559814, "min": 0.04904970410167992, "max": 7.379755293019116, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.3982507406617515, "min": 2.3982507406617515, "max": 118.07608468830585, "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": "1697016972", "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 V2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cu118", "numpy_version": "1.21.2", "end_time_seconds": "1697019303" }, "total": 2331.076256431, "count": 1, "self": 0.48035659000015585, "children": { "run_training.setup": { "total": 0.04397408300019379, "count": 1, "self": 0.04397408300019379 }, "TrainerController.start_learning": { "total": 2330.5519257579995, "count": 1, "self": 1.6238535508900895, "children": { "TrainerController._reset_env": { "total": 3.7216097270002138, "count": 1, "self": 3.7216097270002138 }, "TrainerController.advance": { "total": 2325.1291281851095, "count": 63316, "self": 1.566923036195476, "children": { "env_step": { "total": 1622.062057330972, "count": 63316, "self": 1485.839115200004, "children": { "SubprocessEnvManager._take_step": { "total": 135.26355448800177, "count": 63316, "self": 4.993670367158757, "children": { "TorchPolicy.evaluate": { "total": 130.26988412084302, "count": 62560, "self": 130.26988412084302 } } }, "workers": { "total": 0.9593876429662487, "count": 63316, "self": 0.0, "children": { "worker_root": { "total": 2325.495550961981, "count": 63316, "is_parallel": true, "self": 964.9432444899144, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020056560001648904, "count": 1, "is_parallel": true, "self": 0.0006361600012496638, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013694959989152267, "count": 8, "is_parallel": true, "self": 0.0013694959989152267 } } }, "UnityEnvironment.step": { "total": 0.08765681999966546, "count": 1, "is_parallel": true, "self": 0.0005577549991357955, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004937700000482437, "count": 1, "is_parallel": true, "self": 0.0004937700000482437 }, "communicator.exchange": { "total": 0.08471973800033084, "count": 1, "is_parallel": true, "self": 0.08471973800033084 }, "steps_from_proto": { "total": 0.001885557000150584, "count": 1, "is_parallel": true, "self": 0.00039294400085054804, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014926129993000359, "count": 8, "is_parallel": true, "self": 0.0014926129993000359 } } } } } } }, "UnityEnvironment.step": { "total": 1360.5523064720664, "count": 63315, "is_parallel": true, "self": 35.12377299516129, "children": { "UnityEnvironment._generate_step_input": { "total": 24.168969467937586, "count": 63315, "is_parallel": true, "self": 24.168969467937586 }, "communicator.exchange": { "total": 1191.4457042949516, "count": 63315, "is_parallel": true, "self": 1191.4457042949516 }, "steps_from_proto": { "total": 109.81385971401596, "count": 63315, "is_parallel": true, "self": 22.217671704017903, "children": { "_process_rank_one_or_two_observation": { "total": 87.59618800999806, "count": 506520, "is_parallel": true, "self": 87.59618800999806 } } } } } } } } } } }, "trainer_advance": { "total": 701.500147817942, "count": 63316, "self": 3.005095362015709, "children": { "process_trajectory": { "total": 123.75213156392829, "count": 63316, "self": 123.57756627792878, "children": { "RLTrainer._checkpoint": { "total": 0.17456528599950616, "count": 2, "self": 0.17456528599950616 } } }, "_update_policy": { "total": 574.742920891998, "count": 453, "self": 370.57453853799143, "children": { "TorchPPOOptimizer.update": { "total": 204.16838235400655, "count": 22755, "self": 204.16838235400655 } } } } } } }, "trainer_threads": { "total": 1.3179997040424496e-06, "count": 1, "self": 1.3179997040424496e-06 }, "TrainerController._save_models": { "total": 0.0773329769999691, "count": 1, "self": 0.001754999000695534, "children": { "RLTrainer._checkpoint": { "total": 0.07557797799927357, "count": 1, "self": 0.07557797799927357 } } } } } } }