{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2701921761035919, "min": 0.26977261900901794, "max": 1.342741847038269, "count": 62 }, "Pyramids.Policy.Entropy.sum": { "value": 8174.9345703125, "min": 8071.5966796875, "max": 40733.41796875, "count": 62 }, "Pyramids.Step.mean": { "value": 1859988.0, "min": 29952.0, "max": 1859988.0, "count": 62 }, "Pyramids.Step.sum": { "value": 1859988.0, "min": 29952.0, "max": 1859988.0, "count": 62 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6743399500846863, "min": -0.10293690860271454, "max": 0.7813393473625183, "count": 62 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 190.8382110595703, "min": -24.80779457092285, "max": 229.71377563476562, "count": 62 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.010546749457716942, "min": -0.02537567913532257, "max": 0.5655151605606079, "count": 62 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.9847300052642822, "min": -6.978311538696289, "max": 134.027099609375, "count": 62 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06926958905560675, "min": 0.06541073590397857, "max": 0.07398475692918068, "count": 62 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9697742467784944, "min": 0.5138031122483441, "max": 1.0930324257596844, "count": 62 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013869414471195168, "min": 7.39460481411504e-05, "max": 0.015861346733499402, "count": 62 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19417180259673236, "min": 0.0010352446739761054, "max": 0.22539597191458666, "count": 62 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00011558203290124762, "min": 0.00011558203290124762, "max": 0.00029838354339596195, "count": 62 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0016181484606174667, "min": 0.0016181484606174667, "max": 0.004117555127481666, "count": 62 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.13852732380952382, "min": 0.13852732380952382, "max": 0.19946118095238097, "count": 62 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.9393825333333334, "min": 1.3962282666666668, "max": 2.8725183333333333, "count": 62 }, "Pyramids.Policy.Beta.mean": { "value": 0.0038588796485714287, "min": 0.0038588796485714287, "max": 0.009946171977142856, "count": 62 }, "Pyramids.Policy.Beta.sum": { "value": 0.05402431508, "min": 0.05402431508, "max": 0.1372645815, "count": 62 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.004745361395180225, "min": 0.004745361395180225, "max": 0.48182225227355957, "count": 62 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.0664350613951683, "min": 0.0664350613951683, "max": 3.372755765914917, "count": 62 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 294.90909090909093, "min": 238.54545454545453, "max": 999.0, "count": 62 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29196.0, "min": 15984.0, "max": 32943.0, "count": 62 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.644464625102101, "min": -1.0000000521540642, "max": 1.7505528300516005, "count": 62 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 162.801997885108, "min": -30.99880162626505, "max": 215.31799809634686, "count": 62 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.644464625102101, "min": -1.0000000521540642, "max": 1.7505528300516005, "count": 62 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 162.801997885108, "min": -30.99880162626505, "max": 215.31799809634686, "count": 62 }, "Pyramids.Policy.RndReward.mean": { "value": 0.014565808352963725, "min": 0.013426007143239113, "max": 10.341735620982945, "count": 62 }, "Pyramids.Policy.RndReward.sum": { "value": 1.4420150269434089, "min": 1.4420150269434089, "max": 165.46776993572712, "count": 62 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 62 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 62 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1701149615", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701156332" }, "total": 6716.385251668, "count": 1, "self": 0.5753307689992653, "children": { "run_training.setup": { "total": 0.06343696700014334, "count": 1, "self": 0.06343696700014334 }, "TrainerController.start_learning": { "total": 6715.746483932, "count": 1, "self": 4.68890463304615, "children": { "TrainerController._reset_env": { "total": 2.810407146999978, "count": 1, "self": 2.810407146999978 }, "TrainerController.advance": { "total": 6707.932427557955, "count": 119611, "self": 4.952084283920158, "children": { "env_step": { "total": 4519.511307172119, "count": 119611, "self": 4196.15482896635, "children": { "SubprocessEnvManager._take_step": { "total": 320.45771707092877, "count": 119611, "self": 14.175374426915141, "children": { "TorchPolicy.evaluate": { "total": 306.2823426440136, "count": 116385, "self": 306.2823426440136 } } }, "workers": { "total": 2.898761134840015, "count": 119610, "self": 0.0, "children": { "worker_root": { "total": 6702.855181220978, "count": 119610, "is_parallel": true, "self": 2854.209973548025, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0027925460001370084, "count": 1, "is_parallel": true, "self": 0.000987173000112307, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018053730000247015, "count": 8, "is_parallel": true, "self": 0.0018053730000247015 } } }, "UnityEnvironment.step": { "total": 0.06999408999990919, "count": 1, "is_parallel": true, "self": 0.0006811949999701028, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005803039998681925, "count": 1, "is_parallel": true, "self": 0.0005803039998681925 }, "communicator.exchange": { "total": 0.0665962479999962, "count": 1, "is_parallel": true, "self": 0.0665962479999962 }, "steps_from_proto": { "total": 0.002136343000074703, "count": 1, "is_parallel": true, "self": 0.00047315000006165064, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016631930000130524, "count": 8, "is_parallel": true, "self": 0.0016631930000130524 } } } } } } }, "UnityEnvironment.step": { "total": 3848.645207672953, "count": 119609, "is_parallel": true, "self": 88.9310091739726, "children": { "UnityEnvironment._generate_step_input": { "total": 54.6570962079079, "count": 119609, "is_parallel": true, "self": 54.6570962079079 }, "communicator.exchange": { "total": 3458.489453091087, "count": 119609, "is_parallel": true, "self": 3458.489453091087 }, "steps_from_proto": { "total": 246.56764919998568, "count": 119609, "is_parallel": true, "self": 53.64709878953158, "children": { "_process_rank_one_or_two_observation": { "total": 192.9205504104541, "count": 956872, "is_parallel": true, "self": 192.9205504104541 } } } } } } } } } } }, "trainer_advance": { "total": 2183.4690361019157, "count": 119610, "self": 9.115496366744082, "children": { "process_trajectory": { "total": 332.01113409218306, "count": 119610, "self": 331.7326709091835, "children": { "RLTrainer._checkpoint": { "total": 0.27846318299953055, "count": 3, "self": 0.27846318299953055 } } }, "_update_policy": { "total": 1842.3424056429885, "count": 857, "self": 742.2272737299331, "children": { "TorchPPOOptimizer.update": { "total": 1100.1151319130554, "count": 42411, "self": 1100.1151319130554 } } } } } } }, "trainer_threads": { "total": 1.481999788666144e-06, "count": 1, "self": 1.481999788666144e-06 }, "TrainerController._save_models": { "total": 0.3147431119996327, "count": 1, "self": 0.009042426999258169, "children": { "RLTrainer._checkpoint": { "total": 0.3057006850003745, "count": 1, "self": 0.3057006850003745 } } } } } } }