{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.35965588688850403, "min": 0.35965588688850403, "max": 1.4686775207519531, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10755.1494140625, "min": 10755.1494140625, "max": 44553.80078125, "count": 33 }, "Pyramids.Step.mean": { "value": 989957.0, "min": 29952.0, "max": 989957.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989957.0, "min": 29952.0, "max": 989957.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5722624063491821, "min": -0.10666599124670029, "max": 0.6460117697715759, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 158.51669311523438, "min": -25.813169479370117, "max": 185.40538024902344, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0067070769146084785, "min": -0.01521294191479683, "max": 0.2853538990020752, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.8578603267669678, "min": -4.198771953582764, "max": 67.62887573242188, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06953370519165349, "min": 0.06561430558698098, "max": 0.07420820221748381, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9734718726831488, "min": 0.4771865699078952, "max": 1.0637702220313563, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014735080271618376, "min": 0.0011499833945067168, "max": 0.017138565461168747, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20629112380265727, "min": 0.013799800734080601, "max": 0.24266550426060954, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.390961822092852e-06, "min": 7.390961822092852e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010347346550929992, "min": 0.00010347346550929992, "max": 0.0036340006886664993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246362142857145, "min": 0.10246362142857145, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4344907000000002, "min": 1.3886848, "max": 2.6113335, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002561157807142856, "min": 0.0002561157807142856, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035856209299999983, "min": 0.0035856209299999983, "max": 0.12115221665, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008464858867228031, "min": 0.008464858867228031, "max": 0.3671267628669739, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11850801855325699, "min": 0.11850801855325699, "max": 2.569887399673462, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 326.4891304347826, "min": 292.88, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30037.0, "min": 15984.0, "max": 33216.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5647782482530759, "min": -1.0000000521540642, "max": 1.6707959860563277, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 143.959598839283, "min": -29.2480016797781, "max": 167.07959860563278, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5647782482530759, "min": -1.0000000521540642, "max": 1.6707959860563277, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 143.959598839283, "min": -29.2480016797781, "max": 167.07959860563278, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.028762343721767968, "min": 0.028237783641970687, "max": 8.277214052155614, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.646135622402653, "min": 2.646135622402653, "max": 132.43542483448982, "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": "1757927769", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1757930003" }, "total": 2233.447151843, "count": 1, "self": 0.4749741810001069, "children": { "run_training.setup": { "total": 0.02235338600007708, "count": 1, "self": 0.02235338600007708 }, "TrainerController.start_learning": { "total": 2232.949824276, "count": 1, "self": 1.2866556579974713, "children": { "TrainerController._reset_env": { "total": 2.0397291340000265, "count": 1, "self": 2.0397291340000265 }, "TrainerController.advance": { "total": 2229.534256068003, "count": 64029, "self": 1.3160116301019116, "children": { "env_step": { "total": 1580.7328833799586, "count": 64029, "self": 1436.5913425829708, "children": { "SubprocessEnvManager._take_step": { "total": 143.32045903498283, "count": 64029, "self": 4.452831958011529, "children": { "TorchPolicy.evaluate": { "total": 138.8676270769713, "count": 62554, "self": 138.8676270769713 } } }, "workers": { "total": 0.8210817620049511, "count": 64029, "self": 0.0, "children": { "worker_root": { "total": 2228.225531045032, "count": 64029, "is_parallel": true, "self": 901.2289121380134, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017677050000202144, "count": 1, "is_parallel": true, "self": 0.0005913880006573891, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011763169993628253, "count": 8, "is_parallel": true, "self": 0.0011763169993628253 } } }, "UnityEnvironment.step": { "total": 0.048361927000087235, "count": 1, "is_parallel": true, "self": 0.0005170050001197524, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045357799990597414, "count": 1, "is_parallel": true, "self": 0.00045357799990597414 }, "communicator.exchange": { "total": 0.04583592900007716, "count": 1, "is_parallel": true, "self": 0.04583592900007716 }, "steps_from_proto": { "total": 0.0015554149999843503, "count": 1, "is_parallel": true, "self": 0.0003555430002961657, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011998719996881846, "count": 8, "is_parallel": true, "self": 0.0011998719996881846 } } } } } } }, "UnityEnvironment.step": { "total": 1326.9966189070185, "count": 64028, "is_parallel": true, "self": 31.299613379061157, "children": { "UnityEnvironment._generate_step_input": { "total": 22.390515943048968, "count": 64028, "is_parallel": true, "self": 22.390515943048968 }, "communicator.exchange": { "total": 1178.6922559668978, "count": 64028, "is_parallel": true, "self": 1178.6922559668978 }, "steps_from_proto": { "total": 94.61423361801053, "count": 64028, "is_parallel": true, "self": 18.920381938037735, "children": { "_process_rank_one_or_two_observation": { "total": 75.6938516799728, "count": 512224, "is_parallel": true, "self": 75.6938516799728 } } } } } } } } } } }, "trainer_advance": { "total": 647.4853610579423, "count": 64029, "self": 2.5008711868549653, "children": { "process_trajectory": { "total": 123.69222133708422, "count": 64029, "self": 123.48987417308467, "children": { "RLTrainer._checkpoint": { "total": 0.20234716399954777, "count": 2, "self": 0.20234716399954777 } } }, "_update_policy": { "total": 521.2922685340031, "count": 454, "self": 290.97091004099434, "children": { "TorchPPOOptimizer.update": { "total": 230.3213584930088, "count": 22794, "self": 230.3213584930088 } } } } } } }, "trainer_threads": { "total": 9.139998837781604e-07, "count": 1, "self": 9.139998837781604e-07 }, "TrainerController._save_models": { "total": 0.08918250199985778, "count": 1, "self": 0.0013128169998708472, "children": { "RLTrainer._checkpoint": { "total": 0.08786968499998693, "count": 1, "self": 0.08786968499998693 } } } } } } }