{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6224933862686157, "min": 0.6046780347824097, "max": 1.5460586547851562, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18674.80078125, "min": 18120.9921875, "max": 46901.234375, "count": 33 }, "Pyramids.Step.mean": { "value": 989961.0, "min": 29952.0, "max": 989961.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989961.0, "min": 29952.0, "max": 989961.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0010081353830173612, "min": -0.08582386374473572, "max": 0.029124975204467773, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -0.2459850311279297, "min": -20.76937484741211, "max": 7.106493949890137, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.007006947882473469, "min": 0.0029481500387191772, "max": 0.21985338628292084, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.7096953392028809, "min": 0.7193486094474792, "max": 52.10525131225586, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.09683992379577781, "min": 0.09383329123009541, "max": 0.10212220701225143, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.3557589331408895, "min": 0.6939137791376762, "max": 1.5163630404272797, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.006958273378563141, "min": 0.0003414318536975358, "max": 0.007762391414794359, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.09741582729988398, "min": 0.004003326905035465, "max": 0.11643587122191539, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.2096133295078574e-05, "min": 1.2096133295078574e-05, "max": 0.0004919177159021714, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00016934586613110003, "min": 0.00016934586613110003, "max": 0.0054216537156693, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10241920714285714, "min": 0.10241920714285714, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4338689, "min": 1.3691136000000002, "max": 2.4018276999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002516787935714287, "min": 0.0002516787935714287, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003523503110000002, "min": 0.003523503110000002, "max": 0.10845463693000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007172178942710161, "min": 0.00697177043184638, "max": 0.13919970393180847, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10041050612926483, "min": 0.09760478883981705, "max": 0.9743978977203369, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 892.7878787878788, "min": 828.5, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29462.0, "min": 15984.0, "max": 32207.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.22652125719821814, "min": -1.0000000521540642, "max": -0.02173338168197208, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -7.475201487541199, "min": -32.000001668930054, "max": -0.7824017405509949, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.22652125719821814, "min": -1.0000000521540642, "max": -0.02173338168197208, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -7.475201487541199, "min": -32.000001668930054, "max": -0.7824017405509949, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06854892430375471, "min": 0.06498265559720393, "max": 4.4980824324302375, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.2621145020239055, "min": 2.112056153564481, "max": 71.9693189188838, "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": "1681021188", "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": "1681023416" }, "total": 2227.782031176, "count": 1, "self": 0.5294409319999431, "children": { "run_training.setup": { "total": 0.1114713419999589, "count": 1, "self": 0.1114713419999589 }, "TrainerController.start_learning": { "total": 2227.141118902, "count": 1, "self": 1.3257063790019856, "children": { "TrainerController._reset_env": { "total": 3.792164423000031, "count": 1, "self": 3.792164423000031 }, "TrainerController.advance": { "total": 2221.9274639479977, "count": 63210, "self": 1.3678116380301617, "children": { "env_step": { "total": 1388.5702176179286, "count": 63210, "self": 1282.9720356289017, "children": { "SubprocessEnvManager._take_step": { "total": 104.80297890395923, "count": 63210, "self": 4.581558986918708, "children": { "TorchPolicy.evaluate": { "total": 100.22141991704052, "count": 62561, "self": 100.22141991704052 } } }, "workers": { "total": 0.7952030850676692, "count": 63210, "self": 0.0, "children": { "worker_root": { "total": 2222.7715639040475, "count": 63210, "is_parallel": true, "self": 1045.7623031440173, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016719079999347741, "count": 1, "is_parallel": true, "self": 0.0005286729999625095, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011432349999722646, "count": 8, "is_parallel": true, "self": 0.0011432349999722646 } } }, "UnityEnvironment.step": { "total": 0.0462968209999417, "count": 1, "is_parallel": true, "self": 0.0006728869996095455, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005168090001461678, "count": 1, "is_parallel": true, "self": 0.0005168090001461678 }, "communicator.exchange": { "total": 0.0435051240001485, "count": 1, "is_parallel": true, "self": 0.0435051240001485 }, "steps_from_proto": { "total": 0.0016020010000374896, "count": 1, "is_parallel": true, "self": 0.0003579859999263135, "children": { "_process_rank_one_or_two_observation": { "total": 0.001244015000111176, "count": 8, "is_parallel": true, "self": 0.001244015000111176 } } } } } } }, "UnityEnvironment.step": { "total": 1177.0092607600302, "count": 63209, "is_parallel": true, "self": 32.35251253411866, "children": { "UnityEnvironment._generate_step_input": { "total": 22.551677151936474, "count": 63209, "is_parallel": true, "self": 22.551677151936474 }, "communicator.exchange": { "total": 1028.8789538059873, "count": 63209, "is_parallel": true, "self": 1028.8789538059873 }, "steps_from_proto": { "total": 93.22611726798777, "count": 63209, "is_parallel": true, "self": 19.49822716398444, "children": { "_process_rank_one_or_two_observation": { "total": 73.72789010400334, "count": 505672, "is_parallel": true, "self": 73.72789010400334 } } } } } } } } } } }, "trainer_advance": { "total": 831.9894346920391, "count": 63210, "self": 2.488231263081161, "children": { "process_trajectory": { "total": 102.58447856995804, "count": 63210, "self": 102.37314917295794, "children": { "RLTrainer._checkpoint": { "total": 0.21132939700009956, "count": 2, "self": 0.21132939700009956 } } }, "_update_policy": { "total": 726.9167248589999, "count": 440, "self": 381.28367667903626, "children": { "TorchPPOOptimizer.update": { "total": 345.6330481799637, "count": 46233, "self": 345.6330481799637 } } } } } } }, "trainer_threads": { "total": 8.639999578008428e-07, "count": 1, "self": 8.639999578008428e-07 }, "TrainerController._save_models": { "total": 0.09578328800034797, "count": 1, "self": 0.0014205880002009508, "children": { "RLTrainer._checkpoint": { "total": 0.09436270000014702, "count": 1, "self": 0.09436270000014702 } } } } } } }