{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.422071635723114, "min": 0.422071635723114, "max": 1.5132286548614502, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12587.8642578125, "min": 12587.8642578125, "max": 45905.3046875, "count": 33 }, "Pyramids.Step.mean": { "value": 989886.0, "min": 29952.0, "max": 989886.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989886.0, "min": 29952.0, "max": 989886.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6275933384895325, "min": -0.09996095299720764, "max": 0.6682064533233643, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 180.74688720703125, "min": -24.09058952331543, "max": 190.4388427734375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.008181886747479439, "min": -0.04465390741825104, "max": 0.32788509130477905, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -2.3563833236694336, "min": -12.592401504516602, "max": 78.69242095947266, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06464568574253159, "min": 0.06464568574253159, "max": 0.07422114249187609, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9696852861379738, "min": 0.5028729667134741, "max": 1.0871423517431444, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01517917571731636, "min": 0.0005626130253311197, "max": 0.01517917571731636, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2276876357597454, "min": 0.006751356303973436, "max": 0.2276876357597454, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.479157506979997e-06, "min": 7.479157506979997e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011218736260469996, "min": 0.00011218736260469996, "max": 0.0035069249310250997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249301999999999, "min": 0.10249301999999999, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5373952999999998, "min": 1.3691136000000002, "max": 2.5689748999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000259052698, "min": 0.000259052698, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038857904699999995, "min": 0.0038857904699999995, "max": 0.11692059251, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007248158100992441, "min": 0.007248158100992441, "max": 0.3603551983833313, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10872237384319305, "min": 0.10486799478530884, "max": 2.522486448287964, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 309.29, "min": 287.40384615384613, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30929.0, "min": 15984.0, "max": 33098.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6106799863278867, "min": -1.0000000521540642, "max": 1.6984148772155985, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 161.06799863278866, "min": -32.000001668930054, "max": 174.40799809247255, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6106799863278867, "min": -1.0000000521540642, "max": 1.6984148772155985, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 161.06799863278866, "min": -32.000001668930054, "max": 174.40799809247255, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02356862095708493, "min": 0.02356862095708493, "max": 7.722775853704661, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.356862095708493, "min": 2.1633324651484145, "max": 123.56441365927458, "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": "1682419552", "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": "1682422415" }, "total": 2862.6273221170004, "count": 1, "self": 0.8926431510008115, "children": { "run_training.setup": { "total": 0.12418018100015615, "count": 1, "self": 0.12418018100015615 }, "TrainerController.start_learning": { "total": 2861.6104987849994, "count": 1, "self": 2.161786741834476, "children": { "TrainerController._reset_env": { "total": 5.591077189999851, "count": 1, "self": 5.591077189999851 }, "TrainerController.advance": { "total": 2853.6907759621654, "count": 64031, "self": 2.2535104044218315, "children": { "env_step": { "total": 2113.630535597904, "count": 64031, "self": 1960.4012911889122, "children": { "SubprocessEnvManager._take_step": { "total": 151.86478463800358, "count": 64031, "self": 6.4070491099819264, "children": { "TorchPolicy.evaluate": { "total": 145.45773552802166, "count": 62565, "self": 145.45773552802166 } } }, "workers": { "total": 1.3644597709881054, "count": 64031, "self": 0.0, "children": { "worker_root": { "total": 2853.61988177036, "count": 64031, "is_parallel": true, "self": 1050.888898607217, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001968698000382574, "count": 1, "is_parallel": true, "self": 0.0005687170014425647, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013999809989400092, "count": 8, "is_parallel": true, "self": 0.0013999809989400092 } } }, "UnityEnvironment.step": { "total": 0.10138852399995812, "count": 1, "is_parallel": true, "self": 0.000603378000050725, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048393999986728886, "count": 1, "is_parallel": true, "self": 0.00048393999986728886 }, "communicator.exchange": { "total": 0.09841282999968826, "count": 1, "is_parallel": true, "self": 0.09841282999968826 }, "steps_from_proto": { "total": 0.0018883760003518546, "count": 1, "is_parallel": true, "self": 0.0003923249996660161, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014960510006858385, "count": 8, "is_parallel": true, "self": 0.0014960510006858385 } } } } } } }, "UnityEnvironment.step": { "total": 1802.7309831631428, "count": 64030, "is_parallel": true, "self": 41.97936773039146, "children": { "UnityEnvironment._generate_step_input": { "total": 28.069950950238308, "count": 64030, "is_parallel": true, "self": 28.069950950238308 }, "communicator.exchange": { "total": 1613.5301478057754, "count": 64030, "is_parallel": true, "self": 1613.5301478057754 }, "steps_from_proto": { "total": 119.15151667673763, "count": 64030, "is_parallel": true, "self": 26.81893368677447, "children": { "_process_rank_one_or_two_observation": { "total": 92.33258298996316, "count": 512240, "is_parallel": true, "self": 92.33258298996316 } } } } } } } } } } }, "trainer_advance": { "total": 737.8067299598397, "count": 64031, "self": 4.196896834826475, "children": { "process_trajectory": { "total": 128.31894823801122, "count": 64031, "self": 127.97126235200994, "children": { "RLTrainer._checkpoint": { "total": 0.3476858860012726, "count": 2, "self": 0.3476858860012726 } } }, "_update_policy": { "total": 605.290884887002, "count": 446, "self": 384.8675363158454, "children": { "TorchPPOOptimizer.update": { "total": 220.42334857115657, "count": 22824, "self": 220.42334857115657 } } } } } } }, "trainer_threads": { "total": 1.3640001270687208e-06, "count": 1, "self": 1.3640001270687208e-06 }, "TrainerController._save_models": { "total": 0.16685752699959266, "count": 1, "self": 0.005556623000302352, "children": { "RLTrainer._checkpoint": { "total": 0.1613009039992903, "count": 1, "self": 0.1613009039992903 } } } } } } }