{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.28666916489601135, "min": 0.2645026743412018, "max": 1.4314700365066528, "count": 45 }, "Pyramids.Policy.Entropy.sum": { "value": 8650.5283203125, "min": 7968.9365234375, "max": 43425.07421875, "count": 45 }, "Pyramids.Step.mean": { "value": 1349996.0, "min": 29886.0, "max": 1349996.0, "count": 45 }, "Pyramids.Step.sum": { "value": 1349996.0, "min": 29886.0, "max": 1349996.0, "count": 45 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7186986804008484, "min": -0.09877406805753708, "max": 0.7862449288368225, "count": 45 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 210.57870483398438, "min": -23.804550170898438, "max": 231.9422607421875, "count": 45 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.020695682615041733, "min": -0.0020851457957178354, "max": 0.2536472976207733, "count": 45 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.063835144042969, "min": -0.5817556977272034, "max": 61.128997802734375, "count": 45 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06693182826550555, "min": 0.06493968514786545, "max": 0.07417342162008543, "count": 45 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9370455957170777, "min": 0.5774562005802386, "max": 1.0609060056877375, "count": 45 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015425430699677143, "min": 0.0008542959154646646, "max": 0.01779258903808936, "count": 45 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21595602979548, "min": 0.011960142816505304, "max": 0.24909624653325102, "count": 45 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00016653106591823095, "min": 0.00016653106591823095, "max": 0.000298406025531325, "count": 45 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0023314349228552335, "min": 0.0023314349228552335, "max": 0.003969795176734966, "count": 45 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.15551034047619047, "min": 0.15551034047619047, "max": 0.19946867499999998, "count": 45 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.177144766666667, "min": 1.5957493999999999, "max": 2.8126043000000003, "count": 45 }, "Pyramids.Policy.Beta.mean": { "value": 0.005555483013571428, "min": 0.005555483013571428, "max": 0.009946920632500002, "count": 45 }, "Pyramids.Policy.Beta.sum": { "value": 0.07777676218999999, "min": 0.07777676218999999, "max": 0.13233417682999998, "count": 45 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010156959295272827, "min": 0.010119530372321606, "max": 0.5349976420402527, "count": 45 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14219743013381958, "min": 0.14219743013381958, "max": 4.2799811363220215, "count": 45 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 267.09565217391304, "min": 250.392, "max": 994.875, "count": 45 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30716.0, "min": 15918.0, "max": 32390.0, "count": 45 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7329043326170548, "min": -0.9297375520691276, "max": 1.733606383562088, "count": 45 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 199.2839982509613, "min": -30.421601682901382, "max": 216.700797945261, "count": 45 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7329043326170548, "min": -0.9297375520691276, "max": 1.733606383562088, "count": 45 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 199.2839982509613, "min": -30.421601682901382, "max": 216.700797945261, "count": 45 }, "Pyramids.Policy.RndReward.mean": { "value": 0.028059009661639878, "min": 0.02772742746845942, "max": 11.318323723040521, "count": 45 }, "Pyramids.Policy.RndReward.sum": { "value": 3.226786111088586, "min": 2.9391073116566986, "max": 181.09317956864834, "count": 45 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 45 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 45 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1695842886", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "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": "1695845334" }, "total": 2448.065191019, "count": 1, "self": 0.22107643899971663, "children": { "run_training.setup": { "total": 0.044287387000167655, "count": 1, "self": 0.044287387000167655 }, "TrainerController.start_learning": { "total": 2447.799827193, "count": 1, "self": 2.1897277659950305, "children": { "TrainerController._reset_env": { "total": 4.302280407999888, "count": 1, "self": 4.302280407999888 }, "TrainerController.advance": { "total": 2441.203795940005, "count": 87366, "self": 2.1587807599480584, "children": { "env_step": { "total": 1603.5822113199972, "count": 87366, "self": 1442.938436330009, "children": { "SubprocessEnvManager._take_step": { "total": 159.26421725393243, "count": 87366, "self": 6.794734602887502, "children": { "TorchPolicy.evaluate": { "total": 152.46948265104493, "count": 84876, "self": 152.46948265104493 } } }, "workers": { "total": 1.3795577360558582, "count": 87366, "self": 0.0, "children": { "worker_root": { "total": 2443.927371398999, "count": 87366, "is_parallel": true, "self": 1147.3639511520369, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021367070000906097, "count": 1, "is_parallel": true, "self": 0.0006627569998727267, "children": { "_process_rank_one_or_two_observation": { "total": 0.001473950000217883, "count": 8, "is_parallel": true, "self": 0.001473950000217883 } } }, "UnityEnvironment.step": { "total": 0.046885526000096434, "count": 1, "is_parallel": true, "self": 0.00043176100007258356, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003626850000273407, "count": 1, "is_parallel": true, "self": 0.0003626850000273407 }, "communicator.exchange": { "total": 0.04411589599999388, "count": 1, "is_parallel": true, "self": 0.04411589599999388 }, "steps_from_proto": { "total": 0.0019751840000026277, "count": 1, "is_parallel": true, "self": 0.0003668509998533409, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016083330001492868, "count": 8, "is_parallel": true, "self": 0.0016083330001492868 } } } } } } }, "UnityEnvironment.step": { "total": 1296.5634202469623, "count": 87365, "is_parallel": true, "self": 33.59425536292679, "children": { "UnityEnvironment._generate_step_input": { "total": 21.941230666021966, "count": 87365, "is_parallel": true, "self": 21.941230666021966 }, "communicator.exchange": { "total": 1139.835950148002, "count": 87365, "is_parallel": true, "self": 1139.835950148002 }, "steps_from_proto": { "total": 101.19198407001159, "count": 87365, "is_parallel": true, "self": 21.147035213946992, "children": { "_process_rank_one_or_two_observation": { "total": 80.0449488560646, "count": 698920, "is_parallel": true, "self": 80.0449488560646 } } } } } } } } } } }, "trainer_advance": { "total": 835.4628038600595, "count": 87366, "self": 4.197077344057561, "children": { "process_trajectory": { "total": 149.8424963540017, "count": 87366, "self": 149.62954606600147, "children": { "RLTrainer._checkpoint": { "total": 0.2129502880002292, "count": 2, "self": 0.2129502880002292 } } }, "_update_policy": { "total": 681.4232301620002, "count": 626, "self": 434.29953350401297, "children": { "TorchPPOOptimizer.update": { "total": 247.12369665798724, "count": 30960, "self": 247.12369665798724 } } } } } } }, "trainer_threads": { "total": 1.032999989547534e-06, "count": 1, "self": 1.032999989547534e-06 }, "TrainerController._save_models": { "total": 0.10402204599995457, "count": 1, "self": 0.0014076620000196272, "children": { "RLTrainer._checkpoint": { "total": 0.10261438399993494, "count": 1, "self": 0.10261438399993494 } } } } } } }