{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4096289277076721, "min": 0.4096289277076721, "max": 1.3979954719543457, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12446.1650390625, "min": 12230.7880859375, "max": 42409.58984375, "count": 33 }, "Pyramids.Step.mean": { "value": 989923.0, "min": 29952.0, "max": 989923.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989923.0, "min": 29952.0, "max": 989923.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5899499654769897, "min": -0.10523834824562073, "max": 0.5899499654769897, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 168.1357421875, "min": -25.572917938232422, "max": 168.1357421875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.007152628619223833, "min": -0.00746766384691, "max": 0.24311743676662445, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.038499116897583, "min": -2.0162692070007324, "max": 58.83441925048828, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06611629746926372, "min": 0.06562484300563945, "max": 0.07309725882359311, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.925628164569692, "min": 0.5014472720775239, "max": 1.0841881164392986, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015604571967005973, "min": 0.0008556266589350509, "max": 0.01590479412310136, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21846400753808362, "min": 0.011978773225090713, "max": 0.23857191184652038, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.382861824792858e-06, "min": 7.382861824792858e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010336006554710001, "min": 0.00010336006554710001, "max": 0.0036337387887538, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246092142857142, "min": 0.10246092142857142, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4344529, "min": 1.3886848, "max": 2.6112461999999996, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002558460507142858, "min": 0.0002558460507142858, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035818447100000013, "min": 0.0035818447100000013, "max": 0.12114349538, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010325870476663113, "min": 0.010325870476663113, "max": 0.45188334584236145, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14456218481063843, "min": 0.14456218481063843, "max": 3.1631834506988525, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 324.2857142857143, "min": 324.2857142857143, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29510.0, "min": 15984.0, "max": 33300.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6317494303643048, "min": -1.0000000521540642, "max": 1.647065203393931, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 148.48919816315174, "min": -28.239601716399193, "max": 151.52999871224165, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6317494303643048, "min": -1.0000000521540642, "max": 1.647065203393931, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 148.48919816315174, "min": -28.239601716399193, "max": 151.52999871224165, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.034757307006217604, "min": 0.034757307006217604, "max": 9.924467749893665, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1629149375658017, "min": 3.1629149375658017, "max": 158.79148399829865, "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": "1687337843", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1687340061" }, "total": 2217.9867094070005, "count": 1, "self": 0.4854551710004671, "children": { "run_training.setup": { "total": 0.038398505000031946, "count": 1, "self": 0.038398505000031946 }, "TrainerController.start_learning": { "total": 2217.4628557309998, "count": 1, "self": 1.5046532739570466, "children": { "TrainerController._reset_env": { "total": 4.130364340999904, "count": 1, "self": 4.130364340999904 }, "TrainerController.advance": { "total": 2211.679717853043, "count": 63895, "self": 1.4538122230087538, "children": { "env_step": { "total": 1564.5711939629764, "count": 63895, "self": 1452.2814354890031, "children": { "SubprocessEnvManager._take_step": { "total": 111.44952134697246, "count": 63895, "self": 4.888510040949313, "children": { "TorchPolicy.evaluate": { "total": 106.56101130602315, "count": 62546, "self": 106.56101130602315 } } }, "workers": { "total": 0.8402371270008189, "count": 63895, "self": 0.0, "children": { "worker_root": { "total": 2212.144258518003, "count": 63895, "is_parallel": true, "self": 874.7242588860067, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017331169999579288, "count": 1, "is_parallel": true, "self": 0.0005020769999646291, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012310399999932997, "count": 8, "is_parallel": true, "self": 0.0012310399999932997 } } }, "UnityEnvironment.step": { "total": 0.04661455499990552, "count": 1, "is_parallel": true, "self": 0.0005796209998152335, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004902460000266728, "count": 1, "is_parallel": true, "self": 0.0004902460000266728 }, "communicator.exchange": { "total": 0.04364966399998593, "count": 1, "is_parallel": true, "self": 0.04364966399998593 }, "steps_from_proto": { "total": 0.001895024000077683, "count": 1, "is_parallel": true, "self": 0.00041853000016089936, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014764939999167837, "count": 8, "is_parallel": true, "self": 0.0014764939999167837 } } } } } } }, "UnityEnvironment.step": { "total": 1337.4199996319962, "count": 63894, "is_parallel": true, "self": 33.601712449974, "children": { "UnityEnvironment._generate_step_input": { "total": 22.637944666065778, "count": 63894, "is_parallel": true, "self": 22.637944666065778 }, "communicator.exchange": { "total": 1179.391800299023, "count": 63894, "is_parallel": true, "self": 1179.391800299023 }, "steps_from_proto": { "total": 101.78854221693337, "count": 63894, "is_parallel": true, "self": 20.021517339758475, "children": { "_process_rank_one_or_two_observation": { "total": 81.76702487717489, "count": 511152, "is_parallel": true, "self": 81.76702487717489 } } } } } } } } } } }, "trainer_advance": { "total": 645.6547116670577, "count": 63895, "self": 2.666867214026297, "children": { "process_trajectory": { "total": 109.75539778402799, "count": 63895, "self": 109.4831421320282, "children": { "RLTrainer._checkpoint": { "total": 0.2722556519997852, "count": 2, "self": 0.2722556519997852 } } }, "_update_policy": { "total": 533.2324466690034, "count": 454, "self": 342.2116900150713, "children": { "TorchPPOOptimizer.update": { "total": 191.02075665393204, "count": 22746, "self": 191.02075665393204 } } } } } } }, "trainer_threads": { "total": 1.3809994925395586e-06, "count": 1, "self": 1.3809994925395586e-06 }, "TrainerController._save_models": { "total": 0.14811888200074463, "count": 1, "self": 0.001883634000478196, "children": { "RLTrainer._checkpoint": { "total": 0.14623524800026644, "count": 1, "self": 0.14623524800026644 } } } } } } }