{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4932537376880646, "min": 0.49260714650154114, "max": 1.4931550025939941, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14781.828125, "min": 14762.451171875, "max": 45296.3515625, "count": 33 }, "Pyramids.Step.mean": { "value": 989896.0, "min": 29952.0, "max": 989896.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989896.0, "min": 29952.0, "max": 989896.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3830755650997162, "min": -0.12279938161373138, "max": 0.44871169328689575, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 102.66425323486328, "min": -29.471851348876953, "max": 121.15216064453125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.12481797486543655, "min": -0.007700951769948006, "max": 0.4408397972583771, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 33.45121765136719, "min": -2.079257011413574, "max": 104.47903442382812, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06575106887889672, "min": 0.06385722308944981, "max": 0.07298132943779716, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.920514964304554, "min": 0.5108693060645801, "max": 1.0678308021257787, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014629137550877028, "min": 0.0002321590937766454, "max": 0.014829713002698206, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2048079257122784, "min": 0.0027859091253197446, "max": 0.21832211638769985, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.753511701242856e-06, "min": 7.753511701242856e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010854916381739999, "min": 0.00010854916381739999, "max": 0.0035079374306875998, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10258447142857144, "min": 0.10258447142857144, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4361826000000002, "min": 1.3886848, "max": 2.5693124000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026818869571428576, "min": 0.00026818869571428576, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037546417400000005, "min": 0.0037546417400000005, "max": 0.11695430875999997, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010856484062969685, "min": 0.010856484062969685, "max": 0.38719943165779114, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15199077129364014, "min": 0.15199077129364014, "max": 2.7103960514068604, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 416.3, "min": 408.93333333333334, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29141.0, "min": 15984.0, "max": 32766.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.326479977049998, "min": -1.0000000521540642, "max": 1.3801013447650492, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 92.85359839349985, "min": -30.997001603245735, "max": 101.32299938052893, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.326479977049998, "min": -1.0000000521540642, "max": 1.3801013447650492, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 92.85359839349985, "min": -30.997001603245735, "max": 101.32299938052893, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04687117344209193, "min": 0.04687117344209193, "max": 7.9189072931185365, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.280982140946435, "min": 3.280982140946435, "max": 126.70251668989658, "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": "1680719449", "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": "1680721557" }, "total": 2108.564166356, "count": 1, "self": 0.47579567900038455, "children": { "run_training.setup": { "total": 0.17678425199983394, "count": 1, "self": 0.17678425199983394 }, "TrainerController.start_learning": { "total": 2107.9115864249998, "count": 1, "self": 1.2827584240249053, "children": { "TrainerController._reset_env": { "total": 4.674190202000318, "count": 1, "self": 4.674190202000318 }, "TrainerController.advance": { "total": 2101.8615441799748, "count": 63553, "self": 1.3820729547492192, "children": { "env_step": { "total": 1483.4717952302085, "count": 63553, "self": 1379.871693017391, "children": { "SubprocessEnvManager._take_step": { "total": 102.83044515291613, "count": 63553, "self": 4.64839628096388, "children": { "TorchPolicy.evaluate": { "total": 98.18204887195225, "count": 62550, "self": 98.18204887195225 } } }, "workers": { "total": 0.7696570599014194, "count": 63553, "self": 0.0, "children": { "worker_root": { "total": 2103.333863883942, "count": 63553, "is_parallel": true, "self": 830.8813718818433, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002670992999810551, "count": 1, "is_parallel": true, "self": 0.0008410119994550769, "children": { "_process_rank_one_or_two_observation": { "total": 0.001829981000355474, "count": 8, "is_parallel": true, "self": 0.001829981000355474 } } }, "UnityEnvironment.step": { "total": 0.048361468999701174, "count": 1, "is_parallel": true, "self": 0.0006892559999869263, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005081139997855644, "count": 1, "is_parallel": true, "self": 0.0005081139997855644 }, "communicator.exchange": { "total": 0.04542014799972094, "count": 1, "is_parallel": true, "self": 0.04542014799972094 }, "steps_from_proto": { "total": 0.001743951000207744, "count": 1, "is_parallel": true, "self": 0.00041593400101191946, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013280169991958246, "count": 8, "is_parallel": true, "self": 0.0013280169991958246 } } } } } } }, "UnityEnvironment.step": { "total": 1272.4524920020986, "count": 63552, "is_parallel": true, "self": 32.56971543399459, "children": { "UnityEnvironment._generate_step_input": { "total": 22.730930821055154, "count": 63552, "is_parallel": true, "self": 22.730930821055154 }, "communicator.exchange": { "total": 1122.865737207204, "count": 63552, "is_parallel": true, "self": 1122.865737207204 }, "steps_from_proto": { "total": 94.28610853984492, "count": 63552, "is_parallel": true, "self": 19.534685374254877, "children": { "_process_rank_one_or_two_observation": { "total": 74.75142316559004, "count": 508416, "is_parallel": true, "self": 74.75142316559004 } } } } } } } } } } }, "trainer_advance": { "total": 617.007675995017, "count": 63553, "self": 2.4224305260240726, "children": { "process_trajectory": { "total": 104.56337798299728, "count": 63553, "self": 104.34741632599844, "children": { "RLTrainer._checkpoint": { "total": 0.21596165699884295, "count": 2, "self": 0.21596165699884295 } } }, "_update_policy": { "total": 510.0218674859957, "count": 447, "self": 325.3888958099278, "children": { "TorchPPOOptimizer.update": { "total": 184.63297167606788, "count": 22788, "self": 184.63297167606788 } } } } } } }, "trainer_threads": { "total": 1.264999809791334e-06, "count": 1, "self": 1.264999809791334e-06 }, "TrainerController._save_models": { "total": 0.09309235399996396, "count": 1, "self": 0.0013743660001637181, "children": { "RLTrainer._checkpoint": { "total": 0.09171798799980024, "count": 1, "self": 0.09171798799980024 } } } } } } }