{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4141167998313904, "min": 0.411013662815094, "max": 1.4232971668243408, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12436.755859375, "min": 12436.755859375, "max": 43177.14453125, "count": 33 }, "Pyramids.Step.mean": { "value": 989975.0, "min": 29952.0, "max": 989975.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989975.0, "min": 29952.0, "max": 989975.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4642117917537689, "min": -0.10046806931495667, "max": 0.5092542767524719, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 124.87297058105469, "min": -23.810932159423828, "max": 137.4986572265625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.13167573511600494, "min": -0.14581912755966187, "max": 0.4110393226146698, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -35.420772552490234, "min": -38.05879211425781, "max": 97.41632080078125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06750942748817819, "min": 0.06615350907980436, "max": 0.0746284401011151, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.8776225573463164, "min": 0.4975102445705802, "max": 1.0544579777827796, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.018620149500439432, "min": 0.0004473318100470182, "max": 0.018620149500439432, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2420619435057126, "min": 0.0053679817205642185, "max": 0.2420619435057126, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.483759043907688e-06, "min": 7.483759043907688e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 9.728886757079994e-05, "min": 9.728886757079994e-05, "max": 0.0032239861253379994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249455384615384, "min": 0.10249455384615384, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.3324292, "min": 1.3324292, "max": 2.4424149000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002592059292307691, "min": 0.0002592059292307691, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003369677079999998, "min": 0.003369677079999998, "max": 0.1074787338, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007736539002507925, "min": 0.007657601498067379, "max": 0.35773372650146484, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10057500749826431, "min": 0.10057500749826431, "max": 2.504136085510254, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 360.5897435897436, "min": 360.5897435897436, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28126.0, "min": 15984.0, "max": 33036.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5046358788624787, "min": -1.0000000521540642, "max": 1.5109243691876166, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 117.36159855127335, "min": -30.99880161881447, "max": 123.89579827338457, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5046358788624787, "min": -1.0000000521540642, "max": 1.5109243691876166, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 117.36159855127335, "min": -30.99880161881447, "max": 123.89579827338457, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.029301034303408906, "min": 0.029301034303408906, "max": 6.561389754991978, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.2854806756658945, "min": 2.2854806756658945, "max": 104.98223607987165, "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": "1680785505", "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 /content/ml-agents/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": "1680787674" }, "total": 2168.505220453, "count": 1, "self": 0.49226752000004126, "children": { "run_training.setup": { "total": 0.11467244999994364, "count": 1, "self": 0.11467244999994364 }, "TrainerController.start_learning": { "total": 2167.8982804830002, "count": 1, "self": 1.37212141097325, "children": { "TrainerController._reset_env": { "total": 4.024291599000094, "count": 1, "self": 4.024291599000094 }, "TrainerController.advance": { "total": 2162.408276598027, "count": 63699, "self": 1.4158054850408917, "children": { "env_step": { "total": 1540.1628943829949, "count": 63699, "self": 1433.5143101488893, "children": { "SubprocessEnvManager._take_step": { "total": 105.8179166170612, "count": 63699, "self": 4.68729074407247, "children": { "TorchPolicy.evaluate": { "total": 101.13062587298873, "count": 62566, "self": 101.13062587298873 } } }, "workers": { "total": 0.8306676170444689, "count": 63699, "self": 0.0, "children": { "worker_root": { "total": 2162.839170732021, "count": 63699, "is_parallel": true, "self": 839.5935490809834, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0052413649999607514, "count": 1, "is_parallel": true, "self": 0.003923440999756167, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013179240002045844, "count": 8, "is_parallel": true, "self": 0.0013179240002045844 } } }, "UnityEnvironment.step": { "total": 0.04897054900004605, "count": 1, "is_parallel": true, "self": 0.0006509330000881164, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047533200006455445, "count": 1, "is_parallel": true, "self": 0.00047533200006455445 }, "communicator.exchange": { "total": 0.046250895999946806, "count": 1, "is_parallel": true, "self": 0.046250895999946806 }, "steps_from_proto": { "total": 0.0015933879999465717, "count": 1, "is_parallel": true, "self": 0.0003883450001467281, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012050429997998435, "count": 8, "is_parallel": true, "self": 0.0012050429997998435 } } } } } } }, "UnityEnvironment.step": { "total": 1323.2456216510377, "count": 63698, "is_parallel": true, "self": 33.81566918206772, "children": { "UnityEnvironment._generate_step_input": { "total": 23.1169495909852, "count": 63698, "is_parallel": true, "self": 23.1169495909852 }, "communicator.exchange": { "total": 1170.9519572509828, "count": 63698, "is_parallel": true, "self": 1170.9519572509828 }, "steps_from_proto": { "total": 95.36104562700211, "count": 63698, "is_parallel": true, "self": 20.3601391459124, "children": { "_process_rank_one_or_two_observation": { "total": 75.00090648108971, "count": 509584, "is_parallel": true, "self": 75.00090648108971 } } } } } } } } } } }, "trainer_advance": { "total": 620.8295767299912, "count": 63699, "self": 2.4374697689837603, "children": { "process_trajectory": { "total": 104.15299514401192, "count": 63699, "self": 103.9316565170119, "children": { "RLTrainer._checkpoint": { "total": 0.22133862700002283, "count": 2, "self": 0.22133862700002283 } } }, "_update_policy": { "total": 514.2391118169955, "count": 443, "self": 328.7940523149838, "children": { "TorchPPOOptimizer.update": { "total": 185.44505950201176, "count": 22812, "self": 185.44505950201176 } } } } } } }, "trainer_threads": { "total": 1.207999957841821e-06, "count": 1, "self": 1.207999957841821e-06 }, "TrainerController._save_models": { "total": 0.09358966699983284, "count": 1, "self": 0.0018555239998931938, "children": { "RLTrainer._checkpoint": { "total": 0.09173414299993965, "count": 1, "self": 0.09173414299993965 } } } } } } }