{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3674517571926117, "min": 0.36686137318611145, "max": 1.4542946815490723, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10994.15625, "min": 10993.8837890625, "max": 44117.484375, "count": 33 }, "Pyramids.Step.mean": { "value": 989986.0, "min": 29952.0, "max": 989986.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989986.0, "min": 29952.0, "max": 989986.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5637838840484619, "min": -0.08810929954051971, "max": 0.5804979801177979, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 158.4232635498047, "min": -20.88190460205078, "max": 163.11993408203125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.029854003340005875, "min": 0.006940348539501429, "max": 0.2831437289714813, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.388975143432617, "min": 1.9155361652374268, "max": 68.23764038085938, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07073411973570251, "min": 0.06491149801253673, "max": 0.07295289211565725, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9902776762998352, "min": 0.5042653728323994, "max": 1.06901109975297, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01563542043960279, "min": 0.0003720302153765909, "max": 0.018016964650713885, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21889588615443903, "min": 0.004464362584519091, "max": 0.2522375051099944, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.672404585421426e-06, "min": 7.672404585421426e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010741366419589998, "min": 0.00010741366419589998, "max": 0.0032582130139291, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025574357142857, "min": 0.1025574357142857, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358041, "min": 1.3886848, "max": 2.5725091000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002654878278571428, "min": 0.0002654878278571428, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00371682959, "min": 0.00371682959, "max": 0.10863848291, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014722021296620369, "min": 0.014722021296620369, "max": 0.43229904770851135, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.20610830187797546, "min": 0.20610830187797546, "max": 3.0260932445526123, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 332.375, "min": 312.30434782608694, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29249.0, "min": 15984.0, "max": 32934.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6221477087925782, "min": -1.0000000521540642, "max": 1.6645656453088076, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 142.74899837374687, "min": -31.999601677060127, "max": 164.79199888557196, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6221477087925782, "min": -1.0000000521540642, "max": 1.6645656453088076, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 142.74899837374687, "min": -31.999601677060127, "max": 164.79199888557196, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05058660220509575, "min": 0.05003421346408196, "max": 7.874740703031421, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.451620994048426, "min": 4.451620994048426, "max": 125.99585124850273, "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": "1741995694", "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 Training1 --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": "1741998003" }, "total": 2309.395940958, "count": 1, "self": 0.47723294400020677, "children": { "run_training.setup": { "total": 0.02025285900003837, "count": 1, "self": 0.02025285900003837 }, "TrainerController.start_learning": { "total": 2308.8984551549997, "count": 1, "self": 1.3223388940041332, "children": { "TrainerController._reset_env": { "total": 3.2741732680001405, "count": 1, "self": 3.2741732680001405 }, "TrainerController.advance": { "total": 2304.2155766909955, "count": 64026, "self": 1.377673573998436, "children": { "env_step": { "total": 1606.0195406379992, "count": 64026, "self": 1456.9362025679645, "children": { "SubprocessEnvManager._take_step": { "total": 148.33473852004067, "count": 64026, "self": 4.552171330008832, "children": { "TorchPolicy.evaluate": { "total": 143.78256719003184, "count": 62571, "self": 143.78256719003184 } } }, "workers": { "total": 0.748599549993969, "count": 64026, "self": 0.0, "children": { "worker_root": { "total": 2304.109060945995, "count": 64026, "is_parallel": true, "self": 957.9049148689412, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005870276999985435, "count": 1, "is_parallel": true, "self": 0.004460993000293456, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014092839996919793, "count": 8, "is_parallel": true, "self": 0.0014092839996919793 } } }, "UnityEnvironment.step": { "total": 0.052287288999878, "count": 1, "is_parallel": true, "self": 0.0005519329997696332, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045146299999032635, "count": 1, "is_parallel": true, "self": 0.00045146299999032635 }, "communicator.exchange": { "total": 0.04961776599998302, "count": 1, "is_parallel": true, "self": 0.04961776599998302 }, "steps_from_proto": { "total": 0.0016661270001350204, "count": 1, "is_parallel": true, "self": 0.00035410500004218193, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013120220000928384, "count": 8, "is_parallel": true, "self": 0.0013120220000928384 } } } } } } }, "UnityEnvironment.step": { "total": 1346.204146077054, "count": 64025, "is_parallel": true, "self": 31.073529368094796, "children": { "UnityEnvironment._generate_step_input": { "total": 22.38195399497954, "count": 64025, "is_parallel": true, "self": 22.38195399497954 }, "communicator.exchange": { "total": 1200.1812544279558, "count": 64025, "is_parallel": true, "self": 1200.1812544279558 }, "steps_from_proto": { "total": 92.56740828602392, "count": 64025, "is_parallel": true, "self": 18.329200319896017, "children": { "_process_rank_one_or_two_observation": { "total": 74.2382079661279, "count": 512200, "is_parallel": true, "self": 74.2382079661279 } } } } } } } } } } }, "trainer_advance": { "total": 696.8183624789976, "count": 64026, "self": 2.597536713989939, "children": { "process_trajectory": { "total": 128.5095661400062, "count": 64026, "self": 128.25593706600625, "children": { "RLTrainer._checkpoint": { "total": 0.25362907399994583, "count": 2, "self": 0.25362907399994583 } } }, "_update_policy": { "total": 565.7112596250015, "count": 451, "self": 316.7110037680377, "children": { "TorchPPOOptimizer.update": { "total": 249.0002558569638, "count": 22854, "self": 249.0002558569638 } } } } } } }, "trainer_threads": { "total": 1.455000074201962e-06, "count": 1, "self": 1.455000074201962e-06 }, "TrainerController._save_models": { "total": 0.08636484699991342, "count": 1, "self": 0.0014482870001302217, "children": { "RLTrainer._checkpoint": { "total": 0.0849165599997832, "count": 1, "self": 0.0849165599997832 } } } } } } }