{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.48850154876708984, "min": 0.48850154876708984, "max": 1.4755275249481201, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14733.20703125, "min": 14733.20703125, "max": 44761.6015625, "count": 33 }, "Pyramids.Step.mean": { "value": 989972.0, "min": 29952.0, "max": 989972.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989972.0, "min": 29952.0, "max": 989972.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7176522016525269, "min": -0.11127028614282608, "max": 0.7176522016525269, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 209.554443359375, "min": -26.816139221191406, "max": 209.554443359375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0437835156917572, "min": 0.008350442163646221, "max": 0.3982731103897095, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 12.784786224365234, "min": 2.313072443008423, "max": 94.3907241821289, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07546330550740961, "min": 0.06476313198408751, "max": 0.07546330550740961, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0564862771037344, "min": 0.49460572164288946, "max": 1.089465714719457, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015976831384163927, "min": 0.00038802330399016234, "max": 0.01612685448748784, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22367563937829496, "min": 0.0038802330399016235, "max": 0.2419028173123176, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.579961759092855e-06, "min": 7.579961759092855e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010611946462729998, "min": 0.00010611946462729998, "max": 0.003136647254451, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252662142857143, "min": 0.10252662142857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4353727, "min": 1.3886848, "max": 2.400546, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026240948071428567, "min": 0.00026240948071428567, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036737327299999996, "min": 0.0036737327299999996, "max": 0.10458034509999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011238059028983116, "min": 0.011238059028983116, "max": 0.46219751238822937, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15733282268047333, "min": 0.15733282268047333, "max": 3.235382556915283, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 260.25210084033614, "min": 252.47368421052633, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30970.0, "min": 15984.0, "max": 32496.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7395762583966983, "min": -1.0000000521540642, "max": 1.7395762583966983, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 205.2699984908104, "min": -31.99920167028904, "max": 205.2699984908104, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7395762583966983, "min": -1.0000000521540642, "max": 1.7395762583966983, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 205.2699984908104, "min": -31.99920167028904, "max": 205.2699984908104, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.030279496394618716, "min": 0.030279496394618716, "max": 9.224788644351065, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.5729805745650083, "min": 3.5204053386405576, "max": 147.59661830961704, "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": "1679531440", "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": "1679533824" }, "total": 2384.234228023, "count": 1, "self": 0.8961950160000924, "children": { "run_training.setup": { "total": 0.169306038000002, "count": 1, "self": 0.169306038000002 }, "TrainerController.start_learning": { "total": 2383.168726969, "count": 1, "self": 1.6546354450665604, "children": { "TrainerController._reset_env": { "total": 9.852543793000052, "count": 1, "self": 9.852543793000052 }, "TrainerController.advance": { "total": 2371.520595146933, "count": 63943, "self": 1.7681283489014277, "children": { "env_step": { "total": 1709.8911882030268, "count": 63943, "self": 1586.2680713330087, "children": { "SubprocessEnvManager._take_step": { "total": 122.64285272801783, "count": 63943, "self": 5.612532301032104, "children": { "TorchPolicy.evaluate": { "total": 117.03032042698572, "count": 62561, "self": 117.03032042698572 } } }, "workers": { "total": 0.9802641420003511, "count": 63943, "self": 0.0, "children": { "worker_root": { "total": 2377.2013677679856, "count": 63943, "is_parallel": true, "self": 923.4828946680141, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007448882000005597, "count": 1, "is_parallel": true, "self": 0.005019197999956759, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024296840000488373, "count": 8, "is_parallel": true, "self": 0.0024296840000488373 } } }, "UnityEnvironment.step": { "total": 0.05169796599994925, "count": 1, "is_parallel": true, "self": 0.0005603649998988658, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005421710000064195, "count": 1, "is_parallel": true, "self": 0.0005421710000064195 }, "communicator.exchange": { "total": 0.04893172700002424, "count": 1, "is_parallel": true, "self": 0.04893172700002424 }, "steps_from_proto": { "total": 0.0016637030000197228, "count": 1, "is_parallel": true, "self": 0.0003772320000052787, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012864710000144441, "count": 8, "is_parallel": true, "self": 0.0012864710000144441 } } } } } } }, "UnityEnvironment.step": { "total": 1453.7184730999716, "count": 63942, "is_parallel": true, "self": 33.96729401390394, "children": { "UnityEnvironment._generate_step_input": { "total": 25.660052194022455, "count": 63942, "is_parallel": true, "self": 25.660052194022455 }, "communicator.exchange": { "total": 1289.1195084210135, "count": 63942, "is_parallel": true, "self": 1289.1195084210135 }, "steps_from_proto": { "total": 104.97161847103172, "count": 63942, "is_parallel": true, "self": 23.163390141994796, "children": { "_process_rank_one_or_two_observation": { "total": 81.80822832903692, "count": 511536, "is_parallel": true, "self": 81.80822832903692 } } } } } } } } } } }, "trainer_advance": { "total": 659.8612785950045, "count": 63943, "self": 2.829841813949315, "children": { "process_trajectory": { "total": 127.94745113905424, "count": 63943, "self": 127.4499458800542, "children": { "RLTrainer._checkpoint": { "total": 0.49750525900003595, "count": 2, "self": 0.49750525900003595 } } }, "_update_policy": { "total": 529.0839856420009, "count": 441, "self": 336.7843891340056, "children": { "TorchPPOOptimizer.update": { "total": 192.29959650799532, "count": 22833, "self": 192.29959650799532 } } } } } } }, "trainer_threads": { "total": 1.5790001270943321e-06, "count": 1, "self": 1.5790001270943321e-06 }, "TrainerController._save_models": { "total": 0.14095100500026092, "count": 1, "self": 0.0020867940002062824, "children": { "RLTrainer._checkpoint": { "total": 0.13886421100005464, "count": 1, "self": 0.13886421100005464 } } } } } } }