{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.13890044391155243, "min": 0.12882627546787262, "max": 1.4660499095916748, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4080.33935546875, "min": 3809.13525390625, "max": 44474.08984375, "count": 100 }, "Pyramids.Step.mean": { "value": 2999997.0, "min": 29909.0, "max": 2999997.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999997.0, "min": 29909.0, "max": 2999997.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8215582966804504, "min": -0.10966800153255463, "max": 0.9387181997299194, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 248.93215942382812, "min": -26.429988861083984, "max": 297.57366943359375, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.00424526073038578, "min": -0.010614451952278614, "max": 0.3451360762119293, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.2863140106201172, "min": -3.1206488609313965, "max": 83.17779541015625, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06943439288477835, "min": 0.06373800226422491, "max": 0.07418909801703556, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9720815003868968, "min": 0.5799489655624273, "max": 1.1073437826853478, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014873189860649986, "min": 0.00013691177504414622, "max": 0.01709814915375318, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2082246580490998, "min": 0.0017798530755739007, "max": 0.23977757649360384, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.450306659454762e-06, "min": 1.450306659454762e-06, "max": 0.0002982536130821292, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.030429323236667e-05, "min": 2.030429323236667e-05, "max": 0.003969181676939465, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1004834023809524, "min": 0.1004834023809524, "max": 0.19941787083333337, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4067676333333334, "min": 1.4067676333333334, "max": 2.7373874000000002, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.829189785714287e-05, "min": 5.829189785714287e-05, "max": 0.00994184529625, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008160865700000002, "min": 0.0008160865700000002, "max": 0.13231374727999998, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008422481827437878, "min": 0.008270560763776302, "max": 0.4001147150993347, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11791474372148514, "min": 0.11578785628080368, "max": 3.2009177207946777, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 223.71851851851852, "min": 188.6772151898734, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30202.0, "min": 17603.0, "max": 33062.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7762814665282214, "min": -0.9997875513508916, "max": 1.804438836390166, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 239.7979979813099, "min": -31.99320164322853, "max": 285.8649982884526, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7762814665282214, "min": -0.9997875513508916, "max": 1.804438836390166, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 239.7979979813099, "min": -31.99320164322853, "max": 285.8649982884526, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.01944257081653362, "min": 0.01685618815326355, "max": 8.307415151761639, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.624747060232039, "min": 2.441687158523564, "max": 149.53347273170948, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1739299876", "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": "1739310569" }, "total": 10692.896516935001, "count": 1, "self": 1.1513881680020859, "children": { "run_training.setup": { "total": 0.048657955000010134, "count": 1, "self": 0.048657955000010134 }, "TrainerController.start_learning": { "total": 10691.696470812, "count": 1, "self": 7.504213856847855, "children": { "TrainerController._reset_env": { "total": 4.04499208499999, "count": 1, "self": 4.04499208499999 }, "TrainerController.advance": { "total": 10680.059724418152, "count": 195793, "self": 7.504272610074622, "children": { "env_step": { "total": 7565.880673197377, "count": 195793, "self": 7096.752272341677, "children": { "SubprocessEnvManager._take_step": { "total": 465.04259544484336, "count": 195793, "self": 21.194651351615676, "children": { "TorchPolicy.evaluate": { "total": 443.8479440932277, "count": 187539, "self": 443.8479440932277 } } }, "workers": { "total": 4.085805410857063, "count": 195793, "self": 0.0, "children": { "worker_root": { "total": 10667.516358226116, "count": 195793, "is_parallel": true, "self": 4098.152263059285, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006329057000016292, "count": 1, "is_parallel": true, "self": 0.004690913000047203, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016381439999690883, "count": 8, "is_parallel": true, "self": 0.0016381439999690883 } } }, "UnityEnvironment.step": { "total": 0.06666788000001134, "count": 1, "is_parallel": true, "self": 0.0007095430000276792, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005070010000167713, "count": 1, "is_parallel": true, "self": 0.0005070010000167713 }, "communicator.exchange": { "total": 0.06328841799995644, "count": 1, "is_parallel": true, "self": 0.06328841799995644 }, "steps_from_proto": { "total": 0.0021629180000104498, "count": 1, "is_parallel": true, "self": 0.0006229220000477653, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015399959999626844, "count": 8, "is_parallel": true, "self": 0.0015399959999626844 } } } } } } }, "UnityEnvironment.step": { "total": 6569.36409516683, "count": 195792, "is_parallel": true, "self": 141.68802110409888, "children": { "UnityEnvironment._generate_step_input": { "total": 92.42842018688094, "count": 195792, "is_parallel": true, "self": 92.42842018688094 }, "communicator.exchange": { "total": 5954.67224972877, "count": 195792, "is_parallel": true, "self": 5954.67224972877 }, "steps_from_proto": { "total": 380.57540414707984, "count": 195792, "is_parallel": true, "self": 83.52462072263097, "children": { "_process_rank_one_or_two_observation": { "total": 297.05078342444887, "count": 1566336, "is_parallel": true, "self": 297.05078342444887 } } } } } } } } } } }, "trainer_advance": { "total": 3106.6747786106994, "count": 195793, "self": 14.38182017159852, "children": { "process_trajectory": { "total": 489.42954349913276, "count": 195793, "self": 488.651617309133, "children": { "RLTrainer._checkpoint": { "total": 0.7779261899997891, "count": 6, "self": 0.7779261899997891 } } }, "_update_policy": { "total": 2602.863414939968, "count": 1404, "self": 1045.1232863626228, "children": { "TorchPPOOptimizer.update": { "total": 1557.7401285773453, "count": 68346, "self": 1557.7401285773453 } } } } } } }, "trainer_threads": { "total": 1.0650001058820635e-06, "count": 1, "self": 1.0650001058820635e-06 }, "TrainerController._save_models": { "total": 0.08753938699919672, "count": 1, "self": 0.002545285999076441, "children": { "RLTrainer._checkpoint": { "total": 0.08499410100012028, "count": 1, "self": 0.08499410100012028 } } } } } } }