{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.40999701619148254, "min": 0.39939722418785095, "max": 1.5147372484207153, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12365.509765625, "min": 11969.1357421875, "max": 45951.0703125, "count": 33 }, "Pyramids.Step.mean": { "value": 989983.0, "min": 29952.0, "max": 989983.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989983.0, "min": 29952.0, "max": 989983.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.43793773651123047, "min": -0.26306644082069397, "max": 0.49982985854148865, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 117.80525207519531, "min": -62.34674835205078, "max": 136.45355224609375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.03153499960899353, "min": -0.03487278148531914, "max": 0.2576129734516144, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -8.482914924621582, "min": -9.10179615020752, "max": 62.342342376708984, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0678381564260538, "min": 0.06415906015272234, "max": 0.0734987230508772, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9497341899647532, "min": 0.4953659168740964, "max": 1.0542711167557477, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01368161584694116, "min": 0.0010486669678227043, "max": 0.015195393866936984, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19154262185717624, "min": 0.012584003613872453, "max": 0.21273551413711778, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.395247534950003e-06, "min": 7.395247534950003e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010353346548930005, "min": 0.00010353346548930005, "max": 0.0035059682313439994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246505000000003, "min": 0.10246505000000003, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4345107000000004, "min": 1.3886848, "max": 2.568656, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002562584950000001, "min": 0.0002562584950000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003587618930000002, "min": 0.003587618930000002, "max": 0.11688873439999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011266748420894146, "min": 0.011266748420894146, "max": 0.37811270356178284, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1577344834804535, "min": 0.1577344834804535, "max": 2.6467888355255127, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 410.3, "min": 367.56976744186045, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28721.0, "min": 15984.0, "max": 32676.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.478357720333086, "min": -1.0000000521540642, "max": 1.511655975182851, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 104.9633981436491, "min": -29.94820163398981, "max": 122.72139853984118, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.478357720333086, "min": -1.0000000521540642, "max": 1.511655975182851, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 104.9633981436491, "min": -29.94820163398981, "max": 122.72139853984118, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04724441887523887, "min": 0.04418748565127745, "max": 7.3193822633475065, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.35435374014196, "min": 3.35435374014196, "max": 117.1101162135601, "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": "1713901103", "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=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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1713902714" }, "total": 1610.7235986870005, "count": 1, "self": 0.3262232740012223, "children": { "run_training.setup": { "total": 0.052066349999677186, "count": 1, "self": 0.052066349999677186 }, "TrainerController.start_learning": { "total": 1610.3453090629996, "count": 1, "self": 1.213733819967274, "children": { "TrainerController._reset_env": { "total": 2.0323906739999984, "count": 1, "self": 2.0323906739999984 }, "TrainerController.advance": { "total": 1607.0201606620321, "count": 63819, "self": 1.1837664341323944, "children": { "env_step": { "total": 1034.8799137969581, "count": 63819, "self": 918.8945612169464, "children": { "SubprocessEnvManager._take_step": { "total": 115.23175521703934, "count": 63819, "self": 4.181860911012791, "children": { "TorchPolicy.evaluate": { "total": 111.04989430602654, "count": 62565, "self": 111.04989430602654 } } }, "workers": { "total": 0.753597362972414, "count": 63819, "self": 0.0, "children": { "worker_root": { "total": 1608.3053119790452, "count": 63819, "is_parallel": true, "self": 782.2504078910288, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021141610000086075, "count": 1, "is_parallel": true, "self": 0.0006164050000734278, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014977559999351797, "count": 8, "is_parallel": true, "self": 0.0014977559999351797 } } }, "UnityEnvironment.step": { "total": 0.035098191000088264, "count": 1, "is_parallel": true, "self": 0.0004190849999758939, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00029301399990799837, "count": 1, "is_parallel": true, "self": 0.00029301399990799837 }, "communicator.exchange": { "total": 0.03325862500014409, "count": 1, "is_parallel": true, "self": 0.03325862500014409 }, "steps_from_proto": { "total": 0.0011274670000602782, "count": 1, "is_parallel": true, "self": 0.0002618920002532832, "children": { "_process_rank_one_or_two_observation": { "total": 0.000865574999806995, "count": 8, "is_parallel": true, "self": 0.000865574999806995 } } } } } } }, "UnityEnvironment.step": { "total": 826.0549040880164, "count": 63818, "is_parallel": true, "self": 20.643056393986626, "children": { "UnityEnvironment._generate_step_input": { "total": 13.310551547000614, "count": 63818, "is_parallel": true, "self": 13.310551547000614 }, "communicator.exchange": { "total": 731.6305056419769, "count": 63818, "is_parallel": true, "self": 731.6305056419769 }, "steps_from_proto": { "total": 60.470790505052264, "count": 63818, "is_parallel": true, "self": 13.045876576373757, "children": { "_process_rank_one_or_two_observation": { "total": 47.42491392867851, "count": 510544, "is_parallel": true, "self": 47.42491392867851 } } } } } } } } } } }, "trainer_advance": { "total": 570.9564804309416, "count": 63819, "self": 2.4353573749376665, "children": { "process_trajectory": { "total": 113.62291081901822, "count": 63819, "self": 113.43906171601793, "children": { "RLTrainer._checkpoint": { "total": 0.18384910300028423, "count": 2, "self": 0.18384910300028423 } } }, "_update_policy": { "total": 454.8982122369857, "count": 455, "self": 269.5720326629935, "children": { "TorchPPOOptimizer.update": { "total": 185.32617957399225, "count": 22806, "self": 185.32617957399225 } } } } } } }, "trainer_threads": { "total": 1.0690000635804608e-06, "count": 1, "self": 1.0690000635804608e-06 }, "TrainerController._save_models": { "total": 0.0790228380001281, "count": 1, "self": 0.001402568999765208, "children": { "RLTrainer._checkpoint": { "total": 0.0776202690003629, "count": 1, "self": 0.0776202690003629 } } } } } } }