{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4197154641151428, "min": 0.272203266620636, "max": 1.5045830011367798, "count": 377 }, "Pyramids.Policy.Entropy.sum": { "value": 12625.041015625, "min": 8148.67724609375, "max": 45643.03125, "count": 377 }, "Pyramids.Step.mean": { "value": 11309921.0, "min": 29952.0, "max": 11309921.0, "count": 377 }, "Pyramids.Step.sum": { "value": 11309921.0, "min": 29952.0, "max": 11309921.0, "count": 377 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7003707885742188, "min": -0.19950847327709198, "max": 0.7662648558616638, "count": 377 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 197.5045623779297, "min": -47.28350830078125, "max": 224.49522399902344, "count": 377 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.003947226796299219, "min": -0.05940214917063713, "max": 0.3908889889717102, "count": 377 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.1131179332733154, "min": -16.513797760009766, "max": 93.8133544921875, "count": 377 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.05026319106469773, "min": 0.04300903675833806, "max": 0.09981689124556614, "count": 377 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.3518423374528841, "min": 0.2035083431895173, "max": 0.698718238718963, "count": 377 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01388661854296169, "min": 0.00031933543865666705, "max": 9.80639659676568, "count": 377 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.09720632980073182, "min": 0.0022353480705966694, "max": 68.64477617735976, "count": 377 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.002322299456875733, "min": 0.002322299456875733, "max": 0.0029990899200303357, "count": 377 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.01625609619813013, "min": 0.011996359680121343, "max": 0.02384890956503635, "count": 377 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.17740998114285714, "min": 0.17740998114285714, "max": 0.19996966400000002, "count": 377 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.241869868, "min": 0.7998786560000001, "max": 1.5949636520000001, "count": 377 }, "Pyramids.Policy.Beta.mean": { "value": 0.007743257116171428, "min": 0.007743257116171428, "max": 0.0099969694336, "count": 377 }, "Pyramids.Policy.Beta.sum": { "value": 0.054202799813199996, "min": 0.0399878777344, "max": 0.0794968688348, "count": 377 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0034704941790550947, "min": 0.0034704941790550947, "max": 0.6667643785476685, "count": 377 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.024293459951877594, "min": 0.024293459951877594, "max": 2.667057514190674, "count": 377 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 316.0, "min": 237.55371900826447, "max": 999.0, "count": 377 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30968.0, "min": 15984.0, "max": 35843.0, "count": 377 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.644698966482673, "min": -1.0000000521540642, "max": 1.7624462644669636, "count": 377 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 162.82519768178463, "min": -29.995001636445522, "max": 218.6787971407175, "count": 377 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.644698966482673, "min": -1.0000000521540642, "max": 1.7624462644669636, "count": 377 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 162.82519768178463, "min": -29.995001636445522, "max": 218.6787971407175, "count": 377 }, "Pyramids.Policy.RndReward.mean": { "value": 0.011586302707398475, "min": 0.009915739200480927, "max": 11.432586884126067, "count": 377 }, "Pyramids.Policy.RndReward.sum": { "value": 1.147043968032449, "min": 1.0746353828071733, "max": 182.92139014601707, "count": 377 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 377 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 377 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1689757960", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "command_line_arguments": "/home/arran/.local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force", "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": "1689767774" }, "total": 9813.438060935005, "count": 1, "self": 0.14997585001401603, "children": { "run_training.setup": { "total": 0.009300467994762585, "count": 1, "self": 0.009300467994762585 }, "TrainerController.start_learning": { "total": 9813.278784616996, "count": 1, "self": 9.232576190959662, "children": { "TrainerController._reset_env": { "total": 2.422013842005981, "count": 1, "self": 2.422013842005981 }, "TrainerController.advance": { "total": 9801.555481683026, "count": 732625, "self": 8.413826392206829, "children": { "env_step": { "total": 6327.068002251006, "count": 732625, "self": 5318.326892920915, "children": { "SubprocessEnvManager._take_step": { "total": 1003.0577777927683, "count": 732625, "self": 25.714818801294314, "children": { "TorchPolicy.evaluate": { "total": 977.342958991474, "count": 707201, "self": 977.342958991474 } } }, "workers": { "total": 5.683331537322374, "count": 732624, "self": 0.0, "children": { "worker_root": { "total": 9801.626357703004, "count": 732624, "is_parallel": true, "self": 5066.491318356275, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0007869589899200946, "count": 1, "is_parallel": true, "self": 0.00021948496578261256, "children": { "_process_rank_one_or_two_observation": { "total": 0.000567474024137482, "count": 8, "is_parallel": true, "self": 0.000567474024137482 } } }, "UnityEnvironment.step": { "total": 0.01652249798644334, "count": 1, "is_parallel": true, "self": 0.00017548198229633272, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020307398517616093, "count": 1, "is_parallel": true, "self": 0.00020307398517616093 }, "communicator.exchange": { "total": 0.015603690000716597, "count": 1, "is_parallel": true, "self": 0.015603690000716597 }, "steps_from_proto": { "total": 0.0005402520182542503, "count": 1, "is_parallel": true, "self": 0.00013721000868827105, "children": { "_process_rank_one_or_two_observation": { "total": 0.00040304200956597924, "count": 8, "is_parallel": true, "self": 0.00040304200956597924 } } } } } } }, "UnityEnvironment.step": { "total": 4735.135039346729, "count": 732623, "is_parallel": true, "self": 148.83361234873882, "children": { "UnityEnvironment._generate_step_input": { "total": 108.86860577567131, "count": 732623, "is_parallel": true, "self": 108.86860577567131 }, "communicator.exchange": { "total": 4039.3383600350353, "count": 732623, "is_parallel": true, "self": 4039.3383600350353 }, "steps_from_proto": { "total": 438.09446118728374, "count": 732623, "is_parallel": true, "self": 100.58675679168664, "children": { "_process_rank_one_or_two_observation": { "total": 337.5077043955971, "count": 5860984, "is_parallel": true, "self": 337.5077043955971 } } } } } } } } } } }, "trainer_advance": { "total": 3466.0736530398135, "count": 732624, "self": 16.990142274677055, "children": { "process_trajectory": { "total": 817.632784697169, "count": 732624, "self": 816.1766611461062, "children": { "RLTrainer._checkpoint": { "total": 1.456123551062774, "count": 22, "self": 1.456123551062774 } } }, "_update_policy": { "total": 2631.4507260679675, "count": 2712, "self": 1861.5610947568202, "children": { "TorchPPOOptimizer.update": { "total": 769.8896313111472, "count": 130515, "self": 769.8896313111472 } } } } } } }, "trainer_threads": { "total": 6.709888111799955e-07, "count": 1, "self": 6.709888111799955e-07 }, "TrainerController._save_models": { "total": 0.06871223001508042, "count": 1, "self": 0.0009454120299778879, "children": { "RLTrainer._checkpoint": { "total": 0.06776681798510253, "count": 1, "self": 0.06776681798510253 } } } } } } }