{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.436242014169693, "min": 0.436242014169693, "max": 1.4636121988296509, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13094.240234375, "min": 13094.240234375, "max": 44400.140625, "count": 33 }, "Pyramids.Step.mean": { "value": 989963.0, "min": 29952.0, "max": 989963.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989963.0, "min": 29952.0, "max": 989963.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5034027099609375, "min": -0.10487513989210129, "max": 0.5034027099609375, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 138.93914794921875, "min": -25.379783630371094, "max": 138.93914794921875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0008503045537509024, "min": -0.0008503045537509024, "max": 0.31303316354751587, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.2346840500831604, "min": -0.2346840500831604, "max": 75.12796020507812, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0694308313035262, "min": 0.06563874812231266, "max": 0.07184012622003341, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9720316382493668, "min": 0.47908612286980434, "max": 1.0776018933005012, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014048831393232656, "min": 0.00031272439702015147, "max": 0.01503226775890826, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1966836395052572, "min": 0.004065417161261969, "max": 0.21045174862471563, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.452826087185715e-06, "min": 7.452826087185715e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010433956522060001, "min": 0.00010433956522060001, "max": 0.0036354349881883995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248424285714286, "min": 0.10248424285714286, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4347794, "min": 1.3886848, "max": 2.6118116000000002, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025817586142857146, "min": 0.00025817586142857146, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036144620600000008, "min": 0.0036144620600000008, "max": 0.12119997884, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007100880146026611, "min": 0.006741122808307409, "max": 0.5128947496414185, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09941232204437256, "min": 0.09437572211027145, "max": 3.5902633666992188, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 372.1975308641975, "min": 372.1975308641975, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30148.0, "min": 15984.0, "max": 32906.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5784098636588932, "min": -1.0000000521540642, "max": 1.5784098636588932, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 127.85119895637035, "min": -30.99500161409378, "max": 127.85119895637035, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5784098636588932, "min": -1.0000000521540642, "max": 1.5784098636588932, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 127.85119895637035, "min": -30.99500161409378, "max": 127.85119895637035, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02777904900740171, "min": 0.02777904900740171, "max": 9.690085615962744, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.2501029695995385, "min": 2.0108259644111968, "max": 155.0413698554039, "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": "1740872337", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1740874766" }, "total": 2429.604701541, "count": 1, "self": 0.47701173200039193, "children": { "run_training.setup": { "total": 0.029845167999610567, "count": 1, "self": 0.029845167999610567 }, "TrainerController.start_learning": { "total": 2429.097844641, "count": 1, "self": 1.4309590500388367, "children": { "TrainerController._reset_env": { "total": 2.7619192890001614, "count": 1, "self": 2.7619192890001614 }, "TrainerController.advance": { "total": 2424.805221040961, "count": 63630, "self": 1.4655971248262176, "children": { "env_step": { "total": 1675.1972993030654, "count": 63630, "self": 1511.4576798019948, "children": { "SubprocessEnvManager._take_step": { "total": 162.88155949501288, "count": 63630, "self": 4.883012785038318, "children": { "TorchPolicy.evaluate": { "total": 157.99854670997456, "count": 62550, "self": 157.99854670997456 } } }, "workers": { "total": 0.8580600060577126, "count": 63630, "self": 0.0, "children": { "worker_root": { "total": 2423.708936611042, "count": 63630, "is_parallel": true, "self": 1030.6948323940537, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022225370003070566, "count": 1, "is_parallel": true, "self": 0.0007071560012263944, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015153809990806621, "count": 8, "is_parallel": true, "self": 0.0015153809990806621 } } }, "UnityEnvironment.step": { "total": 0.05142218799983311, "count": 1, "is_parallel": true, "self": 0.0005950780000603118, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005439679998744396, "count": 1, "is_parallel": true, "self": 0.0005439679998744396 }, "communicator.exchange": { "total": 0.0484688679998726, "count": 1, "is_parallel": true, "self": 0.0484688679998726 }, "steps_from_proto": { "total": 0.0018142740000257618, "count": 1, "is_parallel": true, "self": 0.00041236299966840306, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014019110003573587, "count": 8, "is_parallel": true, "self": 0.0014019110003573587 } } } } } } }, "UnityEnvironment.step": { "total": 1393.0141042169885, "count": 63629, "is_parallel": true, "self": 34.78714936805454, "children": { "UnityEnvironment._generate_step_input": { "total": 24.298614166058996, "count": 63629, "is_parallel": true, "self": 24.298614166058996 }, "communicator.exchange": { "total": 1229.7742229069968, "count": 63629, "is_parallel": true, "self": 1229.7742229069968 }, "steps_from_proto": { "total": 104.15411777587815, "count": 63629, "is_parallel": true, "self": 20.999436375795995, "children": { "_process_rank_one_or_two_observation": { "total": 83.15468140008215, "count": 509032, "is_parallel": true, "self": 83.15468140008215 } } } } } } } } } } }, "trainer_advance": { "total": 748.1423246130694, "count": 63630, "self": 2.732457192998936, "children": { "process_trajectory": { "total": 136.63605194907632, "count": 63630, "self": 136.41278076207664, "children": { "RLTrainer._checkpoint": { "total": 0.22327118699968196, "count": 2, "self": 0.22327118699968196 } } }, "_update_policy": { "total": 608.7738154709941, "count": 454, "self": 336.236192447996, "children": { "TorchPPOOptimizer.update": { "total": 272.5376230229981, "count": 22794, "self": 272.5376230229981 } } } } } } }, "trainer_threads": { "total": 1.0280000424245372e-06, "count": 1, "self": 1.0280000424245372e-06 }, "TrainerController._save_models": { "total": 0.09974423299991031, "count": 1, "self": 0.0018836620001820847, "children": { "RLTrainer._checkpoint": { "total": 0.09786057099972822, "count": 1, "self": 0.09786057099972822 } } } } } } }