{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3440145254135132, "min": 0.3440145254135132, "max": 1.3726773262023926, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10314.931640625, "min": 10314.931640625, "max": 41641.5390625, "count": 33 }, "Pyramids.Step.mean": { "value": 989889.0, "min": 29952.0, "max": 989889.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989889.0, "min": 29952.0, "max": 989889.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.19457244873046875, "min": -0.0919269248843193, "max": 0.25103047490119934, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 49.810546875, "min": -22.154388427734375, "max": 63.510711669921875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.04745763540267944, "min": 0.018474172800779343, "max": 0.6961549520492554, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 12.149154663085938, "min": 4.692440032958984, "max": 164.9887237548828, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06981380618434209, "min": 0.06592539849123323, "max": 0.07295266340414312, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9773932865807892, "min": 0.4994162615606409, "max": 1.0500790023361333, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01312271847497854, "min": 0.00010816470467537368, "max": 0.03395611554122129, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18371805864969956, "min": 0.0014061411607798578, "max": 0.23769280878854906, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.26491900696429e-06, "min": 7.26491900696429e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010170886609750006, "min": 0.00010170886609750006, "max": 0.0036337084887638994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10242160714285715, "min": 0.10242160714285715, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4339025, "min": 1.3886848, "max": 2.6112361, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002519185535714287, "min": 0.0002519185535714287, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003526859750000002, "min": 0.003526859750000002, "max": 0.12114248639, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.020488804206252098, "min": 0.02033108100295067, "max": 0.8400415182113647, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.28684327006340027, "min": 0.28684327006340027, "max": 5.880290508270264, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 625.7659574468086, "min": 595.4117647058823, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29411.0, "min": 15984.0, "max": 33004.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.9485531569795406, "min": -1.0000000521540642, "max": 1.0353173629745194, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 44.581998378038406, "min": -30.99600163847208, "max": 51.6285986751318, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.9485531569795406, "min": -1.0000000521540642, "max": 1.0353173629745194, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 44.581998378038406, "min": -30.99600163847208, "max": 51.6285986751318, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.1289114409963541, "min": 0.12508267049641147, "max": 18.561645328998566, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 6.058837726828642, "min": 6.058837726828642, "max": 296.98632526397705, "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": "1730210684", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1730212935" }, "total": 2250.675231306, "count": 1, "self": 0.4774125180001647, "children": { "run_training.setup": { "total": 0.05073662399991008, "count": 1, "self": 0.05073662399991008 }, "TrainerController.start_learning": { "total": 2250.147082164, "count": 1, "self": 1.346636996043344, "children": { "TrainerController._reset_env": { "total": 2.1099823160002416, "count": 1, "self": 2.1099823160002416 }, "TrainerController.advance": { "total": 2246.603044322956, "count": 63369, "self": 1.4108572389536675, "children": { "env_step": { "total": 1563.3537105749697, "count": 63369, "self": 1414.2163356890642, "children": { "SubprocessEnvManager._take_step": { "total": 148.33046963407605, "count": 63369, "self": 4.5943996600694845, "children": { "TorchPolicy.evaluate": { "total": 143.73606997400657, "count": 62568, "self": 143.73606997400657 } } }, "workers": { "total": 0.8069052518294484, "count": 63369, "self": 0.0, "children": { "worker_root": { "total": 2244.9206494940904, "count": 63369, "is_parallel": true, "self": 945.8106156260051, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0034005720003733586, "count": 1, "is_parallel": true, "self": 0.000788171001659066, "children": { "_process_rank_one_or_two_observation": { "total": 0.0026124009987142927, "count": 8, "is_parallel": true, "self": 0.0026124009987142927 } } }, "UnityEnvironment.step": { "total": 0.047868164999727014, "count": 1, "is_parallel": true, "self": 0.0006714309993185452, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044333300002108444, "count": 1, "is_parallel": true, "self": 0.00044333300002108444 }, "communicator.exchange": { "total": 0.04515637200029232, "count": 1, "is_parallel": true, "self": 0.04515637200029232 }, "steps_from_proto": { "total": 0.0015970290000950627, "count": 1, "is_parallel": true, "self": 0.0003317710002193053, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012652579998757574, "count": 8, "is_parallel": true, "self": 0.0012652579998757574 } } } } } } }, "UnityEnvironment.step": { "total": 1299.1100338680853, "count": 63368, "is_parallel": true, "self": 32.9174826352978, "children": { "UnityEnvironment._generate_step_input": { "total": 23.623387613952673, "count": 63368, "is_parallel": true, "self": 23.623387613952673 }, "communicator.exchange": { "total": 1145.560702884918, "count": 63368, "is_parallel": true, "self": 1145.560702884918 }, "steps_from_proto": { "total": 97.00846073391676, "count": 63368, "is_parallel": true, "self": 19.830405215850078, "children": { "_process_rank_one_or_two_observation": { "total": 77.17805551806669, "count": 506944, "is_parallel": true, "self": 77.17805551806669 } } } } } } } } } } }, "trainer_advance": { "total": 681.8384765090327, "count": 63369, "self": 2.5658449099373684, "children": { "process_trajectory": { "total": 133.13779556409781, "count": 63369, "self": 132.8779298680979, "children": { "RLTrainer._checkpoint": { "total": 0.25986569599990617, "count": 2, "self": 0.25986569599990617 } } }, "_update_policy": { "total": 546.1348360349975, "count": 448, "self": 308.28890335200504, "children": { "TorchPPOOptimizer.update": { "total": 237.8459326829925, "count": 22800, "self": 237.8459326829925 } } } } } } }, "trainer_threads": { "total": 1.2390000847517513e-06, "count": 1, "self": 1.2390000847517513e-06 }, "TrainerController._save_models": { "total": 0.08741729000030318, "count": 1, "self": 0.0014766080003028037, "children": { "RLTrainer._checkpoint": { "total": 0.08594068200000038, "count": 1, "self": 0.08594068200000038 } } } } } } }