{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2854841649532318, "min": 0.2854841649532318, "max": 1.4154000282287598, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8505.14453125, "min": 8505.14453125, "max": 42937.57421875, "count": 33 }, "Pyramids.Step.mean": { "value": 989965.0, "min": 29952.0, "max": 989965.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989965.0, "min": 29952.0, "max": 989965.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5380781292915344, "min": -0.1813896894454956, "max": 0.658840537071228, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 149.04763793945312, "min": -42.989356994628906, "max": 185.79302978515625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03434540703892708, "min": 0.015651674941182137, "max": 0.42752373218536377, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 9.513677597045898, "min": 4.265201568603516, "max": 103.46074676513672, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0685779968581028, "min": 0.0660657144714302, "max": 0.07435072959783603, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9600919560134392, "min": 0.5204551071848522, "max": 1.0644576423995509, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01523101373813839, "min": 0.0008257898888246052, "max": 0.016578410120841693, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21323419233393748, "min": 0.010735268554719868, "max": 0.2320977416917837, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.269419005464289e-06, "min": 7.269419005464289e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010177186607650004, "min": 0.00010177186607650004, "max": 0.0036048939983687, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10242310714285714, "min": 0.10242310714285714, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4339235, "min": 1.3886848, "max": 2.5266940000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025206840357142876, "min": 0.00025206840357142876, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035289576500000027, "min": 0.0035289576500000027, "max": 0.12017296687, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.02345777489244938, "min": 0.023306602612137794, "max": 0.5046831369400024, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.3284088373184204, "min": 0.3262924253940582, "max": 3.5327820777893066, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 320.1046511627907, "min": 296.5327102803738, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27529.0, "min": 15984.0, "max": 33016.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6093717480407042, "min": -1.0000000521540642, "max": 1.6576315650030187, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 136.79659858345985, "min": -29.717601627111435, "max": 176.26919832080603, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6093717480407042, "min": -1.0000000521540642, "max": 1.6576315650030187, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 136.79659858345985, "min": -29.717601627111435, "max": 176.26919832080603, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07750615950687514, "min": 0.07378721924359415, "max": 9.841219818219543, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 6.588023558084387, "min": 6.588023558084387, "max": 157.45951709151268, "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": "1696631497", "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": "2.0.1+cu118", "numpy_version": "1.21.2", "end_time_seconds": "1696633950" }, "total": 2452.9398904189998, "count": 1, "self": 0.8419328749996566, "children": { "run_training.setup": { "total": 0.04173157200011701, "count": 1, "self": 0.04173157200011701 }, "TrainerController.start_learning": { "total": 2452.056225972, "count": 1, "self": 1.6859025000476322, "children": { "TrainerController._reset_env": { "total": 2.9538506960000177, "count": 1, "self": 2.9538506960000177 }, "TrainerController.advance": { "total": 2447.284342763952, "count": 63983, "self": 1.706042210866599, "children": { "env_step": { "total": 1733.4422111110553, "count": 63983, "self": 1591.4266220280904, "children": { "SubprocessEnvManager._take_step": { "total": 140.97585563196571, "count": 63983, "self": 5.197727181061964, "children": { "TorchPolicy.evaluate": { "total": 135.77812845090375, "count": 62564, "self": 135.77812845090375 } } }, "workers": { "total": 1.0397334509991651, "count": 63983, "self": 0.0, "children": { "worker_root": { "total": 2446.6463196419963, "count": 63983, "is_parallel": true, "self": 990.8659546669844, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019441649999407673, "count": 1, "is_parallel": true, "self": 0.0005836100001488376, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013605549997919297, "count": 8, "is_parallel": true, "self": 0.0013605549997919297 } } }, "UnityEnvironment.step": { "total": 0.050160807999873214, "count": 1, "is_parallel": true, "self": 0.000607435999882, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005511809999916295, "count": 1, "is_parallel": true, "self": 0.0005511809999916295 }, "communicator.exchange": { "total": 0.046957893000126205, "count": 1, "is_parallel": true, "self": 0.046957893000126205 }, "steps_from_proto": { "total": 0.002044297999873379, "count": 1, "is_parallel": true, "self": 0.000428157999749601, "children": { "_process_rank_one_or_two_observation": { "total": 0.001616140000123778, "count": 8, "is_parallel": true, "self": 0.001616140000123778 } } } } } } }, "UnityEnvironment.step": { "total": 1455.780364975012, "count": 63982, "is_parallel": true, "self": 35.474274943891714, "children": { "UnityEnvironment._generate_step_input": { "total": 25.189340771054503, "count": 63982, "is_parallel": true, "self": 25.189340771054503 }, "communicator.exchange": { "total": 1279.5685740119952, "count": 63982, "is_parallel": true, "self": 1279.5685740119952 }, "steps_from_proto": { "total": 115.54817524807049, "count": 63982, "is_parallel": true, "self": 23.698084128074925, "children": { "_process_rank_one_or_two_observation": { "total": 91.85009111999557, "count": 511856, "is_parallel": true, "self": 91.85009111999557 } } } } } } } } } } }, "trainer_advance": { "total": 712.13608944203, "count": 63983, "self": 3.0134299739725066, "children": { "process_trajectory": { "total": 132.9066247980477, "count": 63983, "self": 132.67384865804706, "children": { "RLTrainer._checkpoint": { "total": 0.23277614000062385, "count": 2, "self": 0.23277614000062385 } } }, "_update_policy": { "total": 576.2160346700098, "count": 456, "self": 366.55661648892124, "children": { "TorchPPOOptimizer.update": { "total": 209.65941818108854, "count": 22761, "self": 209.65941818108854 } } } } } } }, "trainer_threads": { "total": 1.4590004866477102e-06, "count": 1, "self": 1.4590004866477102e-06 }, "TrainerController._save_models": { "total": 0.13212855300025694, "count": 1, "self": 0.0022349040000335663, "children": { "RLTrainer._checkpoint": { "total": 0.12989364900022338, "count": 1, "self": 0.12989364900022338 } } } } } } }