{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2474353015422821, "min": 0.23159538209438324, "max": 1.469873070716858, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 7419.10009765625, "min": 6940.4501953125, "max": 44590.0703125, "count": 33 }, "Pyramids.Step.mean": { "value": 989915.0, "min": 29952.0, "max": 989915.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989915.0, "min": 29952.0, "max": 989915.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.48337823152542114, "min": -0.1106615960597992, "max": 0.5074862241744995, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 134.379150390625, "min": -26.780105590820312, "max": 140.06619262695312, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.014540888369083405, "min": -0.00047346134670078754, "max": 0.19412077963352203, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.042366981506348, "min": -0.12120610475540161, "max": 46.588985443115234, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06320304523632374, "min": 0.06279694376284335, "max": 0.07474889665154325, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.8848426333085323, "min": 0.499753800888503, "max": 1.0464845531216054, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01795882434990268, "min": 0.0009152508792207111, "max": 0.01795882434990268, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.25142354089863755, "min": 0.00816958857971279, "max": 0.25142354089863755, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.641826024185714e-06, "min": 7.641826024185714e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001069855643386, "min": 0.0001069855643386, "max": 0.0036335443888185995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254724285714287, "min": 0.10254724285714287, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4356614, "min": 1.3691136000000002, "max": 2.611181400000001, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002644695614285715, "min": 0.0002644695614285715, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003702573860000001, "min": 0.003702573860000001, "max": 0.12113702186, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009209240786731243, "min": 0.008885732851922512, "max": 0.3093952536582947, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12892937660217285, "min": 0.12440025806427002, "max": 2.165766716003418, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 342.07142857142856, "min": 342.07142857142856, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28734.0, "min": 15984.0, "max": 32953.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.562671403977133, "min": -1.0000000521540642, "max": 1.562671403977133, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 131.26439793407917, "min": -32.000001668930054, "max": 131.26439793407917, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.562671403977133, "min": -1.0000000521540642, "max": 1.562671403977133, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 131.26439793407917, "min": -32.000001668930054, "max": 131.26439793407917, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03281182914794217, "min": 0.03281182914794217, "max": 5.673404227010906, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.7561936484271428, "min": 2.7561936484271428, "max": 90.77446763217449, "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": "1682397648", "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 --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": "1682399714" }, "total": 2065.926767803, "count": 1, "self": 0.5331070149995867, "children": { "run_training.setup": { "total": 0.10339683899996999, "count": 1, "self": 0.10339683899996999 }, "TrainerController.start_learning": { "total": 2065.2902639490003, "count": 1, "self": 1.3247687700181814, "children": { "TrainerController._reset_env": { "total": 4.0309583769999335, "count": 1, "self": 4.0309583769999335 }, "TrainerController.advance": { "total": 2059.844028360982, "count": 63894, "self": 1.384299413156441, "children": { "env_step": { "total": 1464.3564275049762, "count": 63894, "self": 1359.6117170390253, "children": { "SubprocessEnvManager._take_step": { "total": 103.91848713596607, "count": 63894, "self": 4.673684678929703, "children": { "TorchPolicy.evaluate": { "total": 99.24480245703637, "count": 62557, "self": 99.24480245703637 } } }, "workers": { "total": 0.8262233299849413, "count": 63894, "self": 0.0, "children": { "worker_root": { "total": 2060.4762316159968, "count": 63894, "is_parallel": true, "self": 810.0260191409761, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016116179999698943, "count": 1, "is_parallel": true, "self": 0.0005214160003106372, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010902019996592571, "count": 8, "is_parallel": true, "self": 0.0010902019996592571 } } }, "UnityEnvironment.step": { "total": 0.10992053999996187, "count": 1, "is_parallel": true, "self": 0.0005894249999300882, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005066560000841491, "count": 1, "is_parallel": true, "self": 0.0005066560000841491 }, "communicator.exchange": { "total": 0.10715988399999787, "count": 1, "is_parallel": true, "self": 0.10715988399999787 }, "steps_from_proto": { "total": 0.0016645749999497639, "count": 1, "is_parallel": true, "self": 0.00038032099996598845, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012842539999837754, "count": 8, "is_parallel": true, "self": 0.0012842539999837754 } } } } } } }, "UnityEnvironment.step": { "total": 1250.4502124750206, "count": 63893, "is_parallel": true, "self": 31.499770319104528, "children": { "UnityEnvironment._generate_step_input": { "total": 23.39437907195827, "count": 63893, "is_parallel": true, "self": 23.39437907195827 }, "communicator.exchange": { "total": 1101.6933306459568, "count": 63893, "is_parallel": true, "self": 1101.6933306459568 }, "steps_from_proto": { "total": 93.8627324380011, "count": 63893, "is_parallel": true, "self": 20.186874947039882, "children": { "_process_rank_one_or_two_observation": { "total": 73.67585749096122, "count": 511144, "is_parallel": true, "self": 73.67585749096122 } } } } } } } } } } }, "trainer_advance": { "total": 594.1033014428496, "count": 63894, "self": 2.653517960870772, "children": { "process_trajectory": { "total": 105.48193396297415, "count": 63894, "self": 105.2462253239737, "children": { "RLTrainer._checkpoint": { "total": 0.2357086390004497, "count": 2, "self": 0.2357086390004497 } } }, "_update_policy": { "total": 485.96784951900463, "count": 454, "self": 308.88678559999676, "children": { "TorchPPOOptimizer.update": { "total": 177.08106391900787, "count": 22794, "self": 177.08106391900787 } } } } } } }, "trainer_threads": { "total": 1.0379999366705306e-06, "count": 1, "self": 1.0379999366705306e-06 }, "TrainerController._save_models": { "total": 0.09050740300017424, "count": 1, "self": 0.0014754570001969114, "children": { "RLTrainer._checkpoint": { "total": 0.08903194599997732, "count": 1, "self": 0.08903194599997732 } } } } } } }