{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.30367034673690796, "min": 0.30367034673690796, "max": 1.503513216972351, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9066.3818359375, "min": 9066.3818359375, "max": 45610.578125, "count": 33 }, "Pyramids.Step.mean": { "value": 989945.0, "min": 29952.0, "max": 989945.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989945.0, "min": 29952.0, "max": 989945.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6827568411827087, "min": -0.12229873239994049, "max": 0.6827568411827087, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 196.63397216796875, "min": -29.351696014404297, "max": 196.63397216796875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0046093761920928955, "min": -0.014909759163856506, "max": 0.17428645491600037, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.327500343322754, "min": -4.294010639190674, "max": 42.00303649902344, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06798597744174292, "min": 0.06366242913922873, "max": 0.07314323919473238, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9518036841844009, "min": 0.4884900576414958, "max": 1.0647121697273927, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014500578650228054, "min": 0.00017935194448627113, "max": 0.01699640228381849, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20300810110319276, "min": 0.0025109272228077957, "max": 0.25494603425727735, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.52789034787857e-06, "min": 7.52789034787857e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010539046487029997, "min": 0.00010539046487029997, "max": 0.0036299755900082004, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250926428571429, "min": 0.10250926428571429, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4351297, "min": 1.3886848, "max": 2.6099918000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002606755021428571, "min": 0.0002606755021428571, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00364945703, "min": 0.00364945703, "max": 0.12101818082, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010678100399672985, "min": 0.010678100399672985, "max": 0.3260381817817688, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14949341118335724, "min": 0.14949341118335724, "max": 2.2822673320770264, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 288.2680412371134, "min": 285.13592233009706, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27962.0, "min": 15984.0, "max": 32758.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7117319488033806, "min": -1.0000000521540642, "max": 1.7117319488033806, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 166.03799903392792, "min": -31.99200166761875, "max": 178.96539752185345, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7117319488033806, "min": -1.0000000521540642, "max": 1.7117319488033806, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 166.03799903392792, "min": -31.99200166761875, "max": 178.96539752185345, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.031906342075672, "min": 0.031906342075672, "max": 5.852329550310969, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.094915181340184, "min": 3.094915181340184, "max": 93.63727280497551, "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": "1679968311", "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": "1679970513" }, "total": 2201.8317717379996, "count": 1, "self": 1.4136154019993228, "children": { "run_training.setup": { "total": 0.10378012099999978, "count": 1, "self": 0.10378012099999978 }, "TrainerController.start_learning": { "total": 2200.3143762150003, "count": 1, "self": 1.3656004269714686, "children": { "TrainerController._reset_env": { "total": 5.906776513000068, "count": 1, "self": 5.906776513000068 }, "TrainerController.advance": { "total": 2192.9501176540284, "count": 64143, "self": 1.4339044139428552, "children": { "env_step": { "total": 1555.828945642985, "count": 64143, "self": 1446.4523566050243, "children": { "SubprocessEnvManager._take_step": { "total": 108.55674772697125, "count": 64143, "self": 4.778990833939815, "children": { "TorchPolicy.evaluate": { "total": 103.77775689303144, "count": 62544, "self": 103.77775689303144 } } }, "workers": { "total": 0.8198413109894318, "count": 64143, "self": 0.0, "children": { "worker_root": { "total": 2195.749684757922, "count": 64143, "is_parallel": true, "self": 866.1649368440146, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017486070000813925, "count": 1, "is_parallel": true, "self": 0.0005575140000928513, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011910929999885411, "count": 8, "is_parallel": true, "self": 0.0011910929999885411 } } }, "UnityEnvironment.step": { "total": 0.04529993699998158, "count": 1, "is_parallel": true, "self": 0.0005577710001034575, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004465530000743456, "count": 1, "is_parallel": true, "self": 0.0004465530000743456 }, "communicator.exchange": { "total": 0.042473954999877606, "count": 1, "is_parallel": true, "self": 0.042473954999877606 }, "steps_from_proto": { "total": 0.001821657999926174, "count": 1, "is_parallel": true, "self": 0.00036100299939789693, "children": { "_process_rank_one_or_two_observation": { "total": 0.001460655000528277, "count": 8, "is_parallel": true, "self": 0.001460655000528277 } } } } } } }, "UnityEnvironment.step": { "total": 1329.5847479139072, "count": 64142, "is_parallel": true, "self": 31.119567578857186, "children": { "UnityEnvironment._generate_step_input": { "total": 22.631784024065382, "count": 64142, "is_parallel": true, "self": 22.631784024065382 }, "communicator.exchange": { "total": 1184.4605005840117, "count": 64142, "is_parallel": true, "self": 1184.4605005840117 }, "steps_from_proto": { "total": 91.37289572697296, "count": 64142, "is_parallel": true, "self": 19.382953459852615, "children": { "_process_rank_one_or_two_observation": { "total": 71.98994226712034, "count": 513136, "is_parallel": true, "self": 71.98994226712034 } } } } } } } } } } }, "trainer_advance": { "total": 635.6872675971006, "count": 64143, "self": 2.519774666033527, "children": { "process_trajectory": { "total": 118.73589292706583, "count": 64143, "self": 118.53630857306598, "children": { "RLTrainer._checkpoint": { "total": 0.1995843539998532, "count": 2, "self": 0.1995843539998532 } } }, "_update_policy": { "total": 514.4316000040012, "count": 450, "self": 327.4008140440301, "children": { "TorchPPOOptimizer.update": { "total": 187.03078595997113, "count": 22800, "self": 187.03078595997113 } } } } } } }, "trainer_threads": { "total": 9.170007615466602e-07, "count": 1, "self": 9.170007615466602e-07 }, "TrainerController._save_models": { "total": 0.09188070399977732, "count": 1, "self": 0.0013525240001399652, "children": { "RLTrainer._checkpoint": { "total": 0.09052817999963736, "count": 1, "self": 0.09052817999963736 } } } } } } }