{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5775616765022278, "min": 0.5775616765022278, "max": 1.5113048553466797, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17206.716796875, "min": 17206.716796875, "max": 45846.9453125, "count": 33 }, "Pyramids.Step.mean": { "value": 989949.0, "min": 29927.0, "max": 989949.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989949.0, "min": 29927.0, "max": 989949.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4286586046218872, "min": -0.1749507039785385, "max": 0.4286586046218872, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 114.02318572998047, "min": -41.46331787109375, "max": 114.02318572998047, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.9057058095932007, "min": -0.054469265043735504, "max": 0.9057058095932007, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 240.91773986816406, "min": -14.21647834777832, "max": 240.91773986816406, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06915697304816285, "min": 0.06275276394345411, "max": 0.0740482274990627, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9681976226742799, "min": 0.5183375924934389, "max": 1.0326431291383307, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.04977741228876842, "min": 9.007309141829469e-05, "max": 0.07835415217954358, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.6968837720427579, "min": 0.0012610232798561257, "max": 1.0969581305136102, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.535883202357144e-06, "min": 7.535883202357144e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010550236483300001, "min": 0.00010550236483300001, "max": 0.0033771178742940996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251192857142856, "min": 0.10251192857142856, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4351669999999999, "min": 1.3886848, "max": 2.4858405, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002609416642857144, "min": 0.0002609416642857144, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036531833000000014, "min": 0.0036531833000000014, "max": 0.11258801941, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005902671255171299, "min": 0.005859593395143747, "max": 0.28719326853752136, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08263739943504333, "min": 0.08203430473804474, "max": 2.010352849960327, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 452.0153846153846, "min": 452.0153846153846, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29381.0, "min": 16854.0, "max": 32652.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4248738139867783, "min": -0.9999500517733395, "max": 1.4248738139867783, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 92.61679790914059, "min": -31.998401656746864, "max": 92.61679790914059, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4248738139867783, "min": -0.9999500517733395, "max": 1.4248738139867783, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 92.61679790914059, "min": -31.998401656746864, "max": 92.61679790914059, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.027363571538948094, "min": 0.027363571538948094, "max": 5.184302484287935, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 1.7786321500316262, "min": 1.7402179265627638, "max": 88.1331422328949, "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": "1677357298", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.22.4", "end_time_seconds": "1677359656" }, "total": 2358.2258431970004, "count": 1, "self": 0.47833200800005216, "children": { "run_training.setup": { "total": 0.17447656800004552, "count": 1, "self": 0.17447656800004552 }, "TrainerController.start_learning": { "total": 2357.5730346210003, "count": 1, "self": 1.6500106140028947, "children": { "TrainerController._reset_env": { "total": 7.329839622999998, "count": 1, "self": 7.329839622999998 }, "TrainerController.advance": { "total": 2348.5055612379974, "count": 63480, "self": 1.7567295518820174, "children": { "env_step": { "total": 1593.678411213048, "count": 63480, "self": 1462.0734517150947, "children": { "SubprocessEnvManager._take_step": { "total": 130.56525121203072, "count": 63480, "self": 5.238861278090326, "children": { "TorchPolicy.evaluate": { "total": 125.32638993394039, "count": 62556, "self": 41.781766839927286, "children": { "TorchPolicy.sample_actions": { "total": 83.5446230940131, "count": 62556, "self": 83.5446230940131 } } } } }, "workers": { "total": 1.039708285922643, "count": 63480, "self": 0.0, "children": { "worker_root": { "total": 2351.4595876139333, "count": 63480, "is_parallel": true, "self": 1020.6273704679409, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002801509999926566, "count": 1, "is_parallel": true, "self": 0.0009315949998836004, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018699150000429654, "count": 8, "is_parallel": true, "self": 0.0018699150000429654 } } }, "UnityEnvironment.step": { "total": 0.04795191700009127, "count": 1, "is_parallel": true, "self": 0.000554534999992029, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005036339998696349, "count": 1, "is_parallel": true, "self": 0.0005036339998696349 }, "communicator.exchange": { "total": 0.045205580000128975, "count": 1, "is_parallel": true, "self": 0.045205580000128975 }, "steps_from_proto": { "total": 0.0016881680001006316, "count": 1, "is_parallel": true, "self": 0.0004210809997857723, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012670870003148593, "count": 8, "is_parallel": true, "self": 0.0012670870003148593 } } } } } } }, "UnityEnvironment.step": { "total": 1330.8322171459924, "count": 63479, "is_parallel": true, "self": 32.76466078892622, "children": { "UnityEnvironment._generate_step_input": { "total": 25.546398870078974, "count": 63479, "is_parallel": true, "self": 25.546398870078974 }, "communicator.exchange": { "total": 1170.4781092179742, "count": 63479, "is_parallel": true, "self": 1170.4781092179742 }, "steps_from_proto": { "total": 102.04304826901307, "count": 63479, "is_parallel": true, "self": 25.238047127010987, "children": { "_process_rank_one_or_two_observation": { "total": 76.80500114200208, "count": 507832, "is_parallel": true, "self": 76.80500114200208 } } } } } } } } } } }, "trainer_advance": { "total": 753.0704204730673, "count": 63480, "self": 2.9856970430234924, "children": { "process_trajectory": { "total": 172.52123982104172, "count": 63480, "self": 172.33289268404155, "children": { "RLTrainer._checkpoint": { "total": 0.18834713700016437, "count": 2, "self": 0.18834713700016437 } } }, "_update_policy": { "total": 577.5634836090021, "count": 451, "self": 222.27255498505883, "children": { "TorchPPOOptimizer.update": { "total": 355.2909286239433, "count": 22770, "self": 355.2909286239433 } } } } } } }, "trainer_threads": { "total": 8.679999154992402e-07, "count": 1, "self": 8.679999154992402e-07 }, "TrainerController._save_models": { "total": 0.08762227799979883, "count": 1, "self": 0.001473958999667957, "children": { "RLTrainer._checkpoint": { "total": 0.08614831900013087, "count": 1, "self": 0.08614831900013087 } } } } } } }