{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.37153637409210205, "min": 0.37153637409210205, "max": 1.3986560106277466, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11152.0361328125, "min": 11152.0361328125, "max": 42429.62890625, "count": 33 }, "Pyramids.Step.mean": { "value": 989875.0, "min": 29922.0, "max": 989875.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989875.0, "min": 29922.0, "max": 989875.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5014972686767578, "min": -0.11548372358083725, "max": 0.615516185760498, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 136.40725708007812, "min": -27.36964225769043, "max": 171.72901916503906, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.056535810232162476, "min": -0.06926246732473373, "max": 0.561869204044342, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -15.377739906311035, "min": -19.324228286743164, "max": 133.16299438476562, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06634535931689675, "min": 0.06482686955582712, "max": 0.07165673572526228, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9288350304365546, "min": 0.46054802762545866, "max": 1.0424821717800417, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01546134001303775, "min": 0.0014314126598446836, "max": 0.018382826918968927, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2164587601825285, "min": 0.017868821166700646, "max": 0.2757424037845339, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.346968979614289e-06, "min": 7.346968979614289e-06, "max": 0.0002952342015886, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010285756571460005, "min": 0.00010285756571460005, "max": 0.0037578460473846995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244895714285716, "min": 0.10244895714285716, "max": 0.1984114, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4342854000000003, "min": 1.3888798, "max": 2.6526153, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025465081857142867, "min": 0.00025465081857142867, "max": 0.00984129886, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035651114600000013, "min": 0.0035651114600000013, "max": 0.12527626847, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.016183989122509956, "min": 0.016183989122509956, "max": 0.6410184502601624, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2265758365392685, "min": 0.2265758365392685, "max": 4.487129211425781, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 375.43589743589746, "min": 304.9375, "max": 987.2424242424242, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29284.0, "min": 16721.0, "max": 32579.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.573266649666505, "min": -0.9275515655224974, "max": 1.6533791540035356, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 122.71479867398739, "min": -30.609201662242413, "max": 159.68539853394032, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.573266649666505, "min": -0.9275515655224974, "max": 1.6533791540035356, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 122.71479867398739, "min": -30.609201662242413, "max": 159.68539853394032, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06233808774954806, "min": 0.05300077534699691, "max": 13.039435151745291, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.862370844464749, "min": 4.862370844464749, "max": 221.67039757966995, "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": "1704029988", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704033579" }, "total": 3591.0262272519994, "count": 1, "self": 1.2004776819990184, "children": { "run_training.setup": { "total": 0.06911664100005055, "count": 1, "self": 0.06911664100005055 }, "TrainerController.start_learning": { "total": 3589.7566329290003, "count": 1, "self": 2.7229789910102227, "children": { "TrainerController._reset_env": { "total": 4.708644239000023, "count": 1, "self": 4.708644239000023 }, "TrainerController.advance": { "total": 3582.18938459199, "count": 63922, "self": 3.2712945478947404, "children": { "env_step": { "total": 2405.860344810014, "count": 63922, "self": 2224.383920032934, "children": { "SubprocessEnvManager._take_step": { "total": 179.68760219104047, "count": 63922, "self": 7.681746104975787, "children": { "TorchPolicy.evaluate": { "total": 172.00585608606468, "count": 62572, "self": 172.00585608606468 } } }, "workers": { "total": 1.7888225860392595, "count": 63922, "self": 0.0, "children": { "worker_root": { "total": 3582.163560618989, "count": 63922, "is_parallel": true, "self": 1564.2782998440384, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00931219299991426, "count": 1, "is_parallel": true, "self": 0.005132059999823468, "children": { "_process_rank_one_or_two_observation": { "total": 0.004180133000090791, "count": 8, "is_parallel": true, "self": 0.004180133000090791 } } }, "UnityEnvironment.step": { "total": 0.07767648000003646, "count": 1, "is_parallel": true, "self": 0.0008157620000019961, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006920570000374937, "count": 1, "is_parallel": true, "self": 0.0006920570000374937 }, "communicator.exchange": { "total": 0.0741032199999836, "count": 1, "is_parallel": true, "self": 0.0741032199999836 }, "steps_from_proto": { "total": 0.0020654410000133794, "count": 1, "is_parallel": true, "self": 0.0004504510001197559, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016149899998936235, "count": 8, "is_parallel": true, "self": 0.0016149899998936235 } } } } } } }, "UnityEnvironment.step": { "total": 2017.8852607749504, "count": 63921, "is_parallel": true, "self": 55.563861940003335, "children": { "UnityEnvironment._generate_step_input": { "total": 30.88520838599584, "count": 63921, "is_parallel": true, "self": 30.88520838599584 }, "communicator.exchange": { "total": 1790.6192530339617, "count": 63921, "is_parallel": true, "self": 1790.6192530339617 }, "steps_from_proto": { "total": 140.81693741498964, "count": 63921, "is_parallel": true, "self": 31.27416615698803, "children": { "_process_rank_one_or_two_observation": { "total": 109.54277125800161, "count": 511368, "is_parallel": true, "self": 109.54277125800161 } } } } } } } } } } }, "trainer_advance": { "total": 1173.0577452340813, "count": 63922, "self": 5.787312613146696, "children": { "process_trajectory": { "total": 188.3830523789327, "count": 63922, "self": 187.95124712893335, "children": { "RLTrainer._checkpoint": { "total": 0.4318052499993428, "count": 2, "self": 0.4318052499993428 } } }, "_update_policy": { "total": 978.8873802420019, "count": 457, "self": 409.4333825799458, "children": { "TorchPPOOptimizer.update": { "total": 569.453997662056, "count": 22803, "self": 569.453997662056 } } } } } } }, "trainer_threads": { "total": 1.5499999790336005e-06, "count": 1, "self": 1.5499999790336005e-06 }, "TrainerController._save_models": { "total": 0.1356235570001445, "count": 1, "self": 0.003266636000262224, "children": { "RLTrainer._checkpoint": { "total": 0.13235692099988228, "count": 1, "self": 0.13235692099988228 } } } } } } }