{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.23059949278831482, "min": 0.2092013955116272, "max": 1.4689029455184937, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 6833.1240234375, "min": 6235.875, "max": 44560.640625, "count": 33 }, "Pyramids.Step.mean": { "value": 989984.0, "min": 29952.0, "max": 989984.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989984.0, "min": 29952.0, "max": 989984.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6300671100616455, "min": -0.09959281235933304, "max": 0.6300671100616455, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 178.93905639648438, "min": -24.10146141052246, "max": 178.93905639648438, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.02351466566324234, "min": -0.02351466566324234, "max": 0.837783932685852, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -6.678164958953857, "min": -6.678164958953857, "max": 201.06814575195312, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.04682658843618508, "min": 0.043318963728822935, "max": 0.05363043942065042, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.6555722381065912, "min": 0.3376627987419765, "max": 0.7719579144225766, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01568849246472209, "min": 0.0018288794884607127, "max": 0.02307932882519838, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21963889450610927, "min": 0.020895796373744297, "max": 0.2568191456375643, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.643497452199998e-06, "min": 7.643497452199998e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010700896433079998, "min": 0.00010700896433079998, "max": 0.0033782231739257, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254780000000001, "min": 0.10254780000000001, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4356692000000002, "min": 1.3691136000000002, "max": 2.5260743, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002645252199999999, "min": 0.0002645252199999999, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003703353079999999, "min": 0.003703353079999999, "max": 0.11263482257, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.03494398295879364, "min": 0.03494398295879364, "max": 1.0783345699310303, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.48921576142311096, "min": 0.48921576142311096, "max": 7.548341751098633, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 312.89690721649487, "min": 310.5816326530612, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30351.0, "min": 15984.0, "max": 32768.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6188632426973508, "min": -1.0000000521540642, "max": 1.6486535861934584, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 158.64859778434038, "min": -32.000001668930054, "max": 159.91939786076546, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6188632426973508, "min": -1.0000000521540642, "max": 1.6486535861934584, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 158.64859778434038, "min": -32.000001668930054, "max": 159.91939786076546, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.11371335865364277, "min": 0.11371335865364277, "max": 14.923394791781902, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 11.143909148056991, "min": 10.510322347516194, "max": 246.4539710879326, "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": "1713803344", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1713805513" }, "total": 2169.7593581450005, "count": 1, "self": 0.6222621180004353, "children": { "run_training.setup": { "total": 0.05733711799985031, "count": 1, "self": 0.05733711799985031 }, "TrainerController.start_learning": { "total": 2169.0797589090002, "count": 1, "self": 1.331322142017143, "children": { "TrainerController._reset_env": { "total": 3.032007926999995, "count": 1, "self": 3.032007926999995 }, "TrainerController.advance": { "total": 2164.5957668149836, "count": 64088, "self": 1.3580681649737016, "children": { "env_step": { "total": 1644.1352480769892, "count": 64088, "self": 1494.3837621958332, "children": { "SubprocessEnvManager._take_step": { "total": 148.95300700406915, "count": 64088, "self": 4.5565507709738995, "children": { "TorchPolicy.evaluate": { "total": 144.39645623309525, "count": 62552, "self": 144.39645623309525 } } }, "workers": { "total": 0.7984788770868363, "count": 64088, "self": 0.0, "children": { "worker_root": { "total": 2164.207150963995, "count": 64088, "is_parallel": true, "self": 787.0951049519731, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005625324999982695, "count": 1, "is_parallel": true, "self": 0.004020959000627045, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016043659993556503, "count": 8, "is_parallel": true, "self": 0.0016043659993556503 } } }, "UnityEnvironment.step": { "total": 0.09752607200016428, "count": 1, "is_parallel": true, "self": 0.002407318000223313, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004636029998437152, "count": 1, "is_parallel": true, "self": 0.0004636029998437152 }, "communicator.exchange": { "total": 0.09308504199998424, "count": 1, "is_parallel": true, "self": 0.09308504199998424 }, "steps_from_proto": { "total": 0.001570109000113007, "count": 1, "is_parallel": true, "self": 0.0003146420003758976, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012554669997371093, "count": 8, "is_parallel": true, "self": 0.0012554669997371093 } } } } } } }, "UnityEnvironment.step": { "total": 1377.112046012022, "count": 64087, "is_parallel": true, "self": 34.417418083825396, "children": { "UnityEnvironment._generate_step_input": { "total": 23.502484587011622, "count": 64087, "is_parallel": true, "self": 23.502484587011622 }, "communicator.exchange": { "total": 1220.6057320191198, "count": 64087, "is_parallel": true, "self": 1220.6057320191198 }, "steps_from_proto": { "total": 98.58641132206503, "count": 64087, "is_parallel": true, "self": 19.607892513246952, "children": { "_process_rank_one_or_two_observation": { "total": 78.97851880881808, "count": 512696, "is_parallel": true, "self": 78.97851880881808 } } } } } } } } } } }, "trainer_advance": { "total": 519.1024505730206, "count": 64088, "self": 2.6458544808056104, "children": { "process_trajectory": { "total": 145.5982032582151, "count": 64088, "self": 145.19442767721466, "children": { "RLTrainer._checkpoint": { "total": 0.4037755810004455, "count": 2, "self": 0.4037755810004455 } } }, "_update_policy": { "total": 370.8583928339999, "count": 450, "self": 250.81502910500922, "children": { "TorchPPOOptimizer.update": { "total": 120.0433637289907, "count": 11337, "self": 120.0433637289907 } } } } } } }, "trainer_threads": { "total": 9.99999429041054e-07, "count": 1, "self": 9.99999429041054e-07 }, "TrainerController._save_models": { "total": 0.12066102500011766, "count": 1, "self": 0.0015415469997606124, "children": { "RLTrainer._checkpoint": { "total": 0.11911947800035705, "count": 1, "self": 0.11911947800035705 } } } } } } }