{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.35679852962493896, "min": 0.35679852962493896, "max": 1.4458413124084473, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10732.5, "min": 10732.5, "max": 43861.04296875, "count": 33 }, "Pyramids.Step.mean": { "value": 989972.0, "min": 29952.0, "max": 989972.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989972.0, "min": 29952.0, "max": 989972.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5421725511550903, "min": -0.11502400040626526, "max": 0.665208637714386, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 150.18179321289062, "min": -27.720783233642578, "max": 189.58445739746094, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.004160713404417038, "min": -0.0011252019321545959, "max": 0.35322853922843933, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.152517557144165, "min": -0.3128061294555664, "max": 84.62960815429688, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06711535931223121, "min": 0.06364875270572669, "max": 0.07235009140070117, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9396150303712371, "min": 0.49188900694228316, "max": 1.0792314634309152, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01621282336471507, "min": 0.0002343982867509289, "max": 0.016271474770855134, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22697952710601094, "min": 0.0030471777277620757, "max": 0.22780064679197187, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4898975033999995e-06, "min": 7.4898975033999995e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001048585650476, "min": 0.0001048585650476, "max": 0.0033728584757138995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249660000000002, "min": 0.10249660000000002, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4349524000000002, "min": 1.3886848, "max": 2.4242861, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025941033999999995, "min": 0.00025941033999999995, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036317447599999997, "min": 0.0036317447599999997, "max": 0.11244618139000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009280407801270485, "min": 0.009280407801270485, "max": 0.48302364349365234, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1299257129430771, "min": 0.1299257129430771, "max": 3.3811655044555664, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 330.752688172043, "min": 299.7291666666667, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30760.0, "min": 15984.0, "max": 32702.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5832064287156187, "min": -1.0000000521540642, "max": 1.6984040296137934, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 147.23819787055254, "min": -30.73400168120861, "max": 168.14199893176556, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5832064287156187, "min": -1.0000000521540642, "max": 1.6984040296137934, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 147.23819787055254, "min": -30.73400168120861, "max": 168.14199893176556, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03212861595356146, "min": 0.030104450516015884, "max": 10.289079973474145, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.9879612836812157, "min": 2.7841255092353094, "max": 164.62527957558632, "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": "1743375193", "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 --force", "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": "1743376332" }, "total": 1138.6493281560251, "count": 1, "self": 1.0724825290963054, "children": { "run_training.setup": { "total": 0.018618091009557247, "count": 1, "self": 0.018618091009557247 }, "TrainerController.start_learning": { "total": 1137.5582275359193, "count": 1, "self": 0.7853155623888597, "children": { "TrainerController._reset_env": { "total": 3.875911117065698, "count": 1, "self": 3.875911117065698 }, "TrainerController.advance": { "total": 1132.8077018995536, "count": 63961, "self": 0.777552910731174, "children": { "env_step": { "total": 683.3575973187108, "count": 63961, "self": 588.5494736894034, "children": { "SubprocessEnvManager._take_step": { "total": 94.33111253927927, "count": 63961, "self": 2.9149739193962887, "children": { "TorchPolicy.evaluate": { "total": 91.41613861988299, "count": 62577, "self": 91.41613861988299 } } }, "workers": { "total": 0.4770110900280997, "count": 63961, "self": 0.0, "children": { "worker_root": { "total": 1136.1145696754102, "count": 63961, "is_parallel": true, "self": 606.6846250903327, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0014298500027507544, "count": 1, "is_parallel": true, "self": 0.0004531999584287405, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009766500443220139, "count": 8, "is_parallel": true, "self": 0.0009766500443220139 } } }, "UnityEnvironment.step": { "total": 0.025487688020803034, "count": 1, "is_parallel": true, "self": 0.00027467694599181414, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00022860709577798843, "count": 1, "is_parallel": true, "self": 0.00022860709577798843 }, "communicator.exchange": { "total": 0.02416202798485756, "count": 1, "is_parallel": true, "self": 0.02416202798485756 }, "steps_from_proto": { "total": 0.0008223759941756725, "count": 1, "is_parallel": true, "self": 0.00019058911129832268, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006317868828773499, "count": 8, "is_parallel": true, "self": 0.0006317868828773499 } } } } } } }, "UnityEnvironment.step": { "total": 529.4299445850775, "count": 63960, "is_parallel": true, "self": 14.461268611834385, "children": { "UnityEnvironment._generate_step_input": { "total": 9.63041244528722, "count": 63960, "is_parallel": true, "self": 9.63041244528722 }, "communicator.exchange": { "total": 460.2224515932612, "count": 63960, "is_parallel": true, "self": 460.2224515932612 }, "steps_from_proto": { "total": 45.11581193469465, "count": 63960, "is_parallel": true, "self": 9.510044377064332, "children": { "_process_rank_one_or_two_observation": { "total": 35.605767557630315, "count": 511680, "is_parallel": true, "self": 35.605767557630315 } } } } } } } } } } }, "trainer_advance": { "total": 448.6725516701117, "count": 63961, "self": 1.4725131987361237, "children": { "process_trajectory": { "total": 86.82653168123215, "count": 63961, "self": 86.52914107823744, "children": { "RLTrainer._checkpoint": { "total": 0.2973906029947102, "count": 2, "self": 0.2973906029947102 } } }, "_update_policy": { "total": 360.37350679014344, "count": 445, "self": 198.5389704372501, "children": { "TorchPPOOptimizer.update": { "total": 161.83453635289334, "count": 22827, "self": 161.83453635289334 } } } } } } }, "trainer_threads": { "total": 7.849885150790215e-07, "count": 1, "self": 7.849885150790215e-07 }, "TrainerController._save_models": { "total": 0.0892981719225645, "count": 1, "self": 0.004541158908978105, "children": { "RLTrainer._checkpoint": { "total": 0.0847570130135864, "count": 1, "self": 0.0847570130135864 } } } } } } }