{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5367006063461304, "min": 0.5367006063461304, "max": 1.4162302017211914, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16178.302734375, "min": 16178.302734375, "max": 42962.7578125, "count": 33 }, "Pyramids.Step.mean": { "value": 989989.0, "min": 29952.0, "max": 989989.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989989.0, "min": 29952.0, "max": 989989.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5026547908782959, "min": -0.1178978756070137, "max": 0.5651812553405762, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 139.738037109375, "min": -28.413387298583984, "max": 155.4248504638672, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.17528997361660004, "min": -0.17528997361660004, "max": 0.48547282814979553, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -48.730613708496094, "min": -48.730613708496094, "max": 115.05706024169922, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07122682727232879, "min": 0.06342198496438665, "max": 0.07465956994980973, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.997175581812603, "min": 0.49143285822657196, "max": 1.0759508394437625, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.02138544465937744, "min": 0.00020126457092603024, "max": 0.02138544465937744, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2993962252312842, "min": 0.002415174851112363, "max": 0.2993962252312842, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.632633170107139e-06, "min": 7.632633170107139e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010685686438149995, "min": 0.00010685686438149995, "max": 0.003224328125224, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254417857142858, "min": 0.10254417857142858, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4356185000000001, "min": 1.3886848, "max": 2.3598006000000002, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026416343928571423, "min": 0.00026416343928571423, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003698288149999999, "min": 0.003698288149999999, "max": 0.1074901224, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009782625362277031, "min": 0.009638218209147453, "max": 0.5478078722953796, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13695675134658813, "min": 0.13493505120277405, "max": 3.8346550464630127, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 386.2325581395349, "min": 317.2823529411765, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 33216.0, "min": 15984.0, "max": 33216.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5439697457260864, "min": -1.0000000521540642, "max": 1.6827176302671432, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 132.78139813244343, "min": -30.63420171290636, "max": 143.03099857270718, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5439697457260864, "min": -1.0000000521540642, "max": 1.6827176302671432, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 132.78139813244343, "min": -30.63420171290636, "max": 143.03099857270718, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.038509702857862614, "min": 0.0325481922543772, "max": 11.958886357024312, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.311834445776185, "min": 2.766596341622062, "max": 191.342181712389, "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": "1678908342", "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": "1678910452" }, "total": 2110.019344376, "count": 1, "self": 0.4927601230001528, "children": { "run_training.setup": { "total": 0.10065590899989729, "count": 1, "self": 0.10065590899989729 }, "TrainerController.start_learning": { "total": 2109.4259283439997, "count": 1, "self": 1.5492565700419618, "children": { "TrainerController._reset_env": { "total": 6.9538583450000715, "count": 1, "self": 6.9538583450000715 }, "TrainerController.advance": { "total": 2100.8325637759576, "count": 63593, "self": 1.5196270880437623, "children": { "env_step": { "total": 1478.8542719929314, "count": 63593, "self": 1365.1409401578806, "children": { "SubprocessEnvManager._take_step": { "total": 112.8218096159992, "count": 63593, "self": 4.976376632028405, "children": { "TorchPolicy.evaluate": { "total": 107.8454329839708, "count": 62538, "self": 107.8454329839708 } } }, "workers": { "total": 0.8915222190516943, "count": 63593, "self": 0.0, "children": { "worker_root": { "total": 2104.3372584719573, "count": 63593, "is_parallel": true, "self": 861.0253495299498, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001995288999978584, "count": 1, "is_parallel": true, "self": 0.000724853000292569, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012704359996860148, "count": 8, "is_parallel": true, "self": 0.0012704359996860148 } } }, "UnityEnvironment.step": { "total": 0.07297649099996306, "count": 1, "is_parallel": true, "self": 0.0004929449999053759, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005257300001630938, "count": 1, "is_parallel": true, "self": 0.0005257300001630938 }, "communicator.exchange": { "total": 0.07025927799986675, "count": 1, "is_parallel": true, "self": 0.07025927799986675 }, "steps_from_proto": { "total": 0.0016985380000278383, "count": 1, "is_parallel": true, "self": 0.00039368800025840756, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013048499997694307, "count": 8, "is_parallel": true, "self": 0.0013048499997694307 } } } } } } }, "UnityEnvironment.step": { "total": 1243.3119089420074, "count": 63592, "is_parallel": true, "self": 31.23475023994547, "children": { "UnityEnvironment._generate_step_input": { "total": 23.86263496200354, "count": 63592, "is_parallel": true, "self": 23.86263496200354 }, "communicator.exchange": { "total": 1091.7523178910346, "count": 63592, "is_parallel": true, "self": 1091.7523178910346 }, "steps_from_proto": { "total": 96.4622058490238, "count": 63592, "is_parallel": true, "self": 21.149377902066362, "children": { "_process_rank_one_or_two_observation": { "total": 75.31282794695744, "count": 508736, "is_parallel": true, "self": 75.31282794695744 } } } } } } } } } } }, "trainer_advance": { "total": 620.4586646949826, "count": 63593, "self": 2.693602664005539, "children": { "process_trajectory": { "total": 120.60300383398044, "count": 63593, "self": 120.4027504679807, "children": { "RLTrainer._checkpoint": { "total": 0.20025336599974253, "count": 2, "self": 0.20025336599974253 } } }, "_update_policy": { "total": 497.16205819699667, "count": 444, "self": 317.1068916519919, "children": { "TorchPPOOptimizer.update": { "total": 180.0551665450048, "count": 22842, "self": 180.0551665450048 } } } } } } }, "trainer_threads": { "total": 8.830002116155811e-07, "count": 1, "self": 8.830002116155811e-07 }, "TrainerController._save_models": { "total": 0.09024877000001652, "count": 1, "self": 0.0013597809997918375, "children": { "RLTrainer._checkpoint": { "total": 0.08888898900022468, "count": 1, "self": 0.08888898900022468 } } } } } } }