{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.48691362142562866, "min": 0.4835819900035858, "max": 1.5011435747146606, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14693.10546875, "min": 14406.875, "max": 45538.69140625, "count": 33 }, "Pyramids.Step.mean": { "value": 989913.0, "min": 29952.0, "max": 989913.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989913.0, "min": 29952.0, "max": 989913.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3981753885746002, "min": -0.09427683800458908, "max": 0.4258575439453125, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 106.31282806396484, "min": -22.81499481201172, "max": 114.55567932128906, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0051437499932944775, "min": 0.0051437499932944775, "max": 0.31874677538871765, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.37338125705719, "min": 1.37338125705719, "max": 75.54298400878906, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06720263277834636, "min": 0.06340403685836853, "max": 0.07331536769368623, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9408368588968491, "min": 0.5104662379304793, "max": 1.0388012104473696, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01342881472976101, "min": 0.00021887230763914541, "max": 0.013465048806111332, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18800340621665412, "min": 0.0028453399993088905, "max": 0.18851068328555864, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.26494043552857e-06, "min": 7.26494043552857e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010170916609739998, "min": 0.00010170916609739998, "max": 0.0033750328749890994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10242161428571431, "min": 0.10242161428571431, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4339026000000004, "min": 1.3886848, "max": 2.4250109, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002519192671428572, "min": 0.0002519192671428572, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035268697400000003, "min": 0.0035268697400000003, "max": 0.11251858891000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008400741964578629, "min": 0.008280488662421703, "max": 0.48458951711654663, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1176103875041008, "min": 0.1176103875041008, "max": 3.3921265602111816, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 445.7096774193548, "min": 445.7096774193548, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27634.0, "min": 15984.0, "max": 33468.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4574806234769282, "min": -1.0000000521540642, "max": 1.4574806234769282, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 90.36379865556955, "min": -31.992801636457443, "max": 94.52719808369875, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4574806234769282, "min": -1.0000000521540642, "max": 1.4574806234769282, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 90.36379865556955, "min": -31.992801636457443, "max": 94.52719808369875, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03911367055327226, "min": 0.03911367055327226, "max": 10.31178966909647, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.42504757430288, "min": 2.42504757430288, "max": 164.98863470554352, "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": "1679689008", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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=Pyramids Training --no-graphics", "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": "1679691179" }, "total": 2171.2356473620002, "count": 1, "self": 0.4849853100004111, "children": { "run_training.setup": { "total": 0.10360009500004708, "count": 1, "self": 0.10360009500004708 }, "TrainerController.start_learning": { "total": 2170.647061957, "count": 1, "self": 1.2947900569865851, "children": { "TrainerController._reset_env": { "total": 6.0556426639998335, "count": 1, "self": 6.0556426639998335 }, "TrainerController.advance": { "total": 2163.1664063900134, "count": 63530, "self": 1.443214681032714, "children": { "env_step": { "total": 1541.5136956600159, "count": 63530, "self": 1435.341317924138, "children": { "SubprocessEnvManager._take_step": { "total": 105.36083039488744, "count": 63530, "self": 4.584346185936965, "children": { "TorchPolicy.evaluate": { "total": 100.77648420895048, "count": 62576, "self": 100.77648420895048 } } }, "workers": { "total": 0.8115473409905007, "count": 63530, "self": 0.0, "children": { "worker_root": { "total": 2165.8552824880067, "count": 63530, "is_parallel": true, "self": 843.0874047269192, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018930290000298555, "count": 1, "is_parallel": true, "self": 0.000576163000005181, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013168660000246746, "count": 8, "is_parallel": true, "self": 0.0013168660000246746 } } }, "UnityEnvironment.step": { "total": 0.0475026120000166, "count": 1, "is_parallel": true, "self": 0.0005337689999578288, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004597399999966001, "count": 1, "is_parallel": true, "self": 0.0004597399999966001 }, "communicator.exchange": { "total": 0.04495155900008285, "count": 1, "is_parallel": true, "self": 0.04495155900008285 }, "steps_from_proto": { "total": 0.0015575439999793161, "count": 1, "is_parallel": true, "self": 0.00034359100004621723, "children": { "_process_rank_one_or_two_observation": { "total": 0.001213952999933099, "count": 8, "is_parallel": true, "self": 0.001213952999933099 } } } } } } }, "UnityEnvironment.step": { "total": 1322.7678777610874, "count": 63529, "is_parallel": true, "self": 31.007937516942775, "children": { "UnityEnvironment._generate_step_input": { "total": 22.255851480028014, "count": 63529, "is_parallel": true, "self": 22.255851480028014 }, "communicator.exchange": { "total": 1178.570662281037, "count": 63529, "is_parallel": true, "self": 1178.570662281037 }, "steps_from_proto": { "total": 90.93342648307976, "count": 63529, "is_parallel": true, "self": 19.089017589072682, "children": { "_process_rank_one_or_two_observation": { "total": 71.84440889400707, "count": 508232, "is_parallel": true, "self": 71.84440889400707 } } } } } } } } } } }, "trainer_advance": { "total": 620.2094960489649, "count": 63530, "self": 2.56144504904546, "children": { "process_trajectory": { "total": 116.63084985191699, "count": 63530, "self": 116.38088960091636, "children": { "RLTrainer._checkpoint": { "total": 0.2499602510006298, "count": 2, "self": 0.2499602510006298 } } }, "_update_policy": { "total": 501.0172011480024, "count": 447, "self": 317.81410646197537, "children": { "TorchPPOOptimizer.update": { "total": 183.20309468602704, "count": 22779, "self": 183.20309468602704 } } } } } } }, "trainer_threads": { "total": 1.3910002962802537e-06, "count": 1, "self": 1.3910002962802537e-06 }, "TrainerController._save_models": { "total": 0.13022145500008264, "count": 1, "self": 0.00157710399980715, "children": { "RLTrainer._checkpoint": { "total": 0.1286443510002755, "count": 1, "self": 0.1286443510002755 } } } } } } }