{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3266650438308716, "min": 0.3266650438308716, "max": 1.4582947492599487, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9789.498046875, "min": 9789.498046875, "max": 44238.828125, "count": 33 }, "Pyramids.Step.mean": { "value": 989999.0, "min": 29952.0, "max": 989999.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989999.0, "min": 29952.0, "max": 989999.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5490950345993042, "min": -0.09387529641389847, "max": 0.6206362247467041, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 153.197509765625, "min": -22.530071258544922, "max": 176.88131713867188, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.026201320812106133, "min": 0.006960572209209204, "max": 0.5513593554496765, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.310168266296387, "min": 1.8236699104309082, "max": 130.6721649169922, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06976140725246374, "min": 0.06438405770706075, "max": 0.07270294635814242, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9766597015344923, "min": 0.5052661671873246, "max": 1.0560003357628982, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016693593044371537, "min": 0.0007555098931293126, "max": 0.01753832545523246, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23371030262120152, "min": 0.009821628610681064, "max": 0.2614222164653862, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.299311852642861e-06, "min": 7.299311852642861e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010219036593700004, "min": 0.00010219036593700004, "max": 0.0034916785361072, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10243307142857143, "min": 0.10243307142857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.434063, "min": 1.3886848, "max": 2.572588, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025306383571428585, "min": 0.00025306383571428585, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035428937000000016, "min": 0.0035428937000000016, "max": 0.11640289072, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012644675560295582, "min": 0.01259064394980669, "max": 0.4685530662536621, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1770254522562027, "min": 0.1770254522562027, "max": 3.2798714637756348, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 316.7282608695652, "min": 295.37254901960785, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29139.0, "min": 15984.0, "max": 32889.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6848064374218705, "min": -1.0000000521540642, "max": 1.6850137129133822, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 156.68699868023396, "min": -29.176201567053795, "max": 171.871398717165, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6848064374218705, "min": -1.0000000521540642, "max": 1.6850137129133822, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 156.68699868023396, "min": -29.176201567053795, "max": 171.871398717165, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04116387796082524, "min": 0.03991603741023402, "max": 9.384377058595419, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.828240650356747, "min": 3.828240650356747, "max": 150.1500329375267, "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": "1746550059", "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": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1746552302" }, "total": 2243.186519125, "count": 1, "self": 0.4249235570005112, "children": { "run_training.setup": { "total": 0.020355562999839094, "count": 1, "self": 0.020355562999839094 }, "TrainerController.start_learning": { "total": 2242.741240005, "count": 1, "self": 1.2465372099886736, "children": { "TrainerController._reset_env": { "total": 2.458327389000033, "count": 1, "self": 2.458327389000033 }, "TrainerController.advance": { "total": 2238.9551998010115, "count": 63992, "self": 1.3739487889183692, "children": { "env_step": { "total": 1564.7346606250567, "count": 63992, "self": 1420.898170588977, "children": { "SubprocessEnvManager._take_step": { "total": 143.1208055060083, "count": 63992, "self": 4.405205390954734, "children": { "TorchPolicy.evaluate": { "total": 138.71560011505358, "count": 62563, "self": 138.71560011505358 } } }, "workers": { "total": 0.7156845300712575, "count": 63992, "self": 0.0, "children": { "worker_root": { "total": 2238.0675776349535, "count": 63992, "is_parallel": true, "self": 925.21445807891, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019860009999774775, "count": 1, "is_parallel": true, "self": 0.0006484669997917081, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013375340001857694, "count": 8, "is_parallel": true, "self": 0.0013375340001857694 } } }, "UnityEnvironment.step": { "total": 0.06980251499999213, "count": 1, "is_parallel": true, "self": 0.0005367019998629985, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004681830000663467, "count": 1, "is_parallel": true, "self": 0.0004681830000663467 }, "communicator.exchange": { "total": 0.06720736700003727, "count": 1, "is_parallel": true, "self": 0.06720736700003727 }, "steps_from_proto": { "total": 0.0015902630000255158, "count": 1, "is_parallel": true, "self": 0.0003251279999858525, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012651350000396633, "count": 8, "is_parallel": true, "self": 0.0012651350000396633 } } } } } } }, "UnityEnvironment.step": { "total": 1312.8531195560436, "count": 63991, "is_parallel": true, "self": 31.009626111055013, "children": { "UnityEnvironment._generate_step_input": { "total": 22.67272188600714, "count": 63991, "is_parallel": true, "self": 22.67272188600714 }, "communicator.exchange": { "total": 1166.6878869099612, "count": 63991, "is_parallel": true, "self": 1166.6878869099612 }, "steps_from_proto": { "total": 92.4828846490202, "count": 63991, "is_parallel": true, "self": 18.095338066972545, "children": { "_process_rank_one_or_two_observation": { "total": 74.38754658204766, "count": 511928, "is_parallel": true, "self": 74.38754658204766 } } } } } } } } } } }, "trainer_advance": { "total": 672.8465903870365, "count": 63992, "self": 2.5367480440361305, "children": { "process_trajectory": { "total": 126.89783910799974, "count": 63992, "self": 126.69576431099972, "children": { "RLTrainer._checkpoint": { "total": 0.20207479700002295, "count": 2, "self": 0.20207479700002295 } } }, "_update_policy": { "total": 543.4120032350006, "count": 455, "self": 304.84422735097974, "children": { "TorchPPOOptimizer.update": { "total": 238.56777588402088, "count": 22770, "self": 238.56777588402088 } } } } } } }, "trainer_threads": { "total": 1.0220001058769412e-06, "count": 1, "self": 1.0220001058769412e-06 }, "TrainerController._save_models": { "total": 0.08117458299966529, "count": 1, "self": 0.0010861819996534905, "children": { "RLTrainer._checkpoint": { "total": 0.0800884010000118, "count": 1, "self": 0.0800884010000118 } } } } } } }