{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3984622657299042, "min": 0.3984622657299042, "max": 1.4428790807724, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11864.6123046875, "min": 11864.6123046875, "max": 43771.1796875, "count": 33 }, "Pyramids.Step.mean": { "value": 989980.0, "min": 29952.0, "max": 989980.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989980.0, "min": 29952.0, "max": 989980.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.44988229870796204, "min": -0.12599356472492218, "max": 0.5194022059440613, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 119.66869354248047, "min": -30.23845672607422, "max": 142.83560180664062, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0030090194195508957, "min": -0.011661017313599586, "max": 0.32013511657714844, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.8003991842269897, "min": -3.090169668197632, "max": 76.83242797851562, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06776188023615673, "min": 0.063663854294767, "max": 0.07333063906817978, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9486663233061942, "min": 0.4529364422716711, "max": 1.0872276475637073, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014251113533169874, "min": 0.00038437434327091917, "max": 0.015955690485656003, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19951558946437822, "min": 0.004228117775980111, "max": 0.22581945180233257, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.473011794742855e-06, "min": 7.473011794742855e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010462216512639997, "min": 0.00010462216512639997, "max": 0.0033807998730667997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249097142857143, "min": 0.10249097142857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4348736, "min": 1.3691136000000002, "max": 2.5276392000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025884804571428565, "min": 0.00025884804571428565, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036238726399999994, "min": 0.0036238726399999994, "max": 0.11272062668, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011145634576678276, "min": 0.011125586926937103, "max": 0.5618067383766174, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15603888034820557, "min": 0.15575821697711945, "max": 3.9326469898223877, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 435.43283582089555, "min": 372.8235294117647, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29174.0, "min": 15984.0, "max": 32804.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.415262664098348, "min": -1.0000000521540642, "max": 1.5724126327830026, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 94.82259849458933, "min": -32.000001668930054, "max": 126.30579826235771, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.415262664098348, "min": -1.0000000521540642, "max": 1.5724126327830026, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 94.82259849458933, "min": -32.000001668930054, "max": 126.30579826235771, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.049970582801303065, "min": 0.043360181540072734, "max": 12.034368934109807, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.348029047687305, "min": 3.348029047687305, "max": 192.5499029457569, "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": "1697197160", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=Pyramids Training --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1697199347" }, "total": 2186.7074896540003, "count": 1, "self": 0.43800380300035613, "children": { "run_training.setup": { "total": 0.08778605399999151, "count": 1, "self": 0.08778605399999151 }, "TrainerController.start_learning": { "total": 2186.181699797, "count": 1, "self": 1.2274726619680223, "children": { "TrainerController._reset_env": { "total": 9.354301114000009, "count": 1, "self": 9.354301114000009 }, "TrainerController.advance": { "total": 2175.5252189640323, "count": 63797, "self": 1.3322385070887321, "children": { "env_step": { "total": 1572.122114739987, "count": 63797, "self": 1451.833844379961, "children": { "SubprocessEnvManager._take_step": { "total": 119.55319098802676, "count": 63797, "self": 4.641003382996814, "children": { "TorchPolicy.evaluate": { "total": 114.91218760502994, "count": 62556, "self": 114.91218760502994 } } }, "workers": { "total": 0.7350793719992907, "count": 63797, "self": 0.0, "children": { "worker_root": { "total": 2181.8300696340675, "count": 63797, "is_parallel": true, "self": 841.460570911054, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006570993999957864, "count": 1, "is_parallel": true, "self": 0.004797954000025584, "children": { "_process_rank_one_or_two_observation": { "total": 0.00177303999993228, "count": 8, "is_parallel": true, "self": 0.00177303999993228 } } }, "UnityEnvironment.step": { "total": 0.04864986899997348, "count": 1, "is_parallel": true, "self": 0.0006363469999541849, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005276009999874987, "count": 1, "is_parallel": true, "self": 0.0005276009999874987 }, "communicator.exchange": { "total": 0.04567057299999533, "count": 1, "is_parallel": true, "self": 0.04567057299999533 }, "steps_from_proto": { "total": 0.0018153480000364652, "count": 1, "is_parallel": true, "self": 0.00038436300002331336, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014309850000131519, "count": 8, "is_parallel": true, "self": 0.0014309850000131519 } } } } } } }, "UnityEnvironment.step": { "total": 1340.3694987230135, "count": 63796, "is_parallel": true, "self": 33.41177490206087, "children": { "UnityEnvironment._generate_step_input": { "total": 22.861748768996506, "count": 63796, "is_parallel": true, "self": 22.861748768996506 }, "communicator.exchange": { "total": 1190.4785039699716, "count": 63796, "is_parallel": true, "self": 1190.4785039699716 }, "steps_from_proto": { "total": 93.6174710819846, "count": 63796, "is_parallel": true, "self": 18.019163598043917, "children": { "_process_rank_one_or_two_observation": { "total": 75.59830748394069, "count": 510368, "is_parallel": true, "self": 75.59830748394069 } } } } } } } } } } }, "trainer_advance": { "total": 602.0708657169564, "count": 63797, "self": 2.3712726920499563, "children": { "process_trajectory": { "total": 117.33308220990483, "count": 63797, "self": 117.09469577190492, "children": { "RLTrainer._checkpoint": { "total": 0.23838643799990678, "count": 2, "self": 0.23838643799990678 } } }, "_update_policy": { "total": 482.3665108150016, "count": 446, "self": 289.3861777850278, "children": { "TorchPPOOptimizer.update": { "total": 192.9803330299738, "count": 22800, "self": 192.9803330299738 } } } } } } }, "trainer_threads": { "total": 1.05399976746412e-06, "count": 1, "self": 1.05399976746412e-06 }, "TrainerController._save_models": { "total": 0.07470600299984653, "count": 1, "self": 0.001397166000060679, "children": { "RLTrainer._checkpoint": { "total": 0.07330883699978585, "count": 1, "self": 0.07330883699978585 } } } } } } }