{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.11958839744329453, "min": 0.11150451749563217, "max": 1.4631630182266235, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 3606.7861328125, "min": 3359.408203125, "max": 44386.51171875, "count": 100 }, "Pyramids.Step.mean": { "value": 2999924.0, "min": 29952.0, "max": 2999924.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999924.0, "min": 29952.0, "max": 2999924.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7341417670249939, "min": -0.10586244612932205, "max": 0.8396094441413879, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 211.43283081054688, "min": -25.406986236572266, "max": 256.08087158203125, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.02374999038875103, "min": -0.042842600494623184, "max": 0.25259140133857727, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -6.839997291564941, "min": -12.724252700805664, "max": 60.87452697753906, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06888409994396835, "min": 0.06530673603145067, "max": 0.0754286819328615, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.964377399215557, "min": 0.4766359016969639, "max": 1.1314302289929223, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01482596761117075, "min": 0.0006062168401217409, "max": 0.01627075131837453, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2075635465563905, "min": 0.005455951561095668, "max": 0.24149069431301792, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5183066367880958e-06, "min": 1.5183066367880958e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.125629291503334e-05, "min": 2.125629291503334e-05, "max": 0.003927410390863233, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10050606904761905, "min": 0.10050606904761905, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4070849666666667, "min": 1.3962282666666668, "max": 2.7825477, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.055629785714289e-05, "min": 6.055629785714289e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008477881700000004, "min": 0.0008477881700000004, "max": 0.13092276299, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.004552434664219618, "min": 0.004354466218501329, "max": 0.40805038809776306, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.06373408436775208, "min": 0.060962527990341187, "max": 2.8563528060913086, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 260.8448275862069, "min": 220.4402985074627, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30258.0, "min": 15984.0, "max": 32568.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7219068759988094, "min": -1.0000000521540642, "max": 1.777558803996619, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 199.7411976158619, "min": -31.999601677060127, "max": 244.91299825906754, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7219068759988094, "min": -1.0000000521540642, "max": 1.777558803996619, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 199.7411976158619, "min": -31.999601677060127, "max": 244.91299825906754, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.012262469078293713, "min": 0.01039818581075587, "max": 8.324369322508574, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.4224464130820706, "min": 1.3553099525124708, "max": 133.18990916013718, "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": "1690177060", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1690182338" }, "total": 5278.600035204, "count": 1, "self": 0.3220644170005471, "children": { "run_training.setup": { "total": 0.0347889849999774, "count": 1, "self": 0.0347889849999774 }, "TrainerController.start_learning": { "total": 5278.2431818019995, "count": 1, "self": 4.088731794095111, "children": { "TrainerController._reset_env": { "total": 4.184307518000196, "count": 1, "self": 4.184307518000196 }, "TrainerController.advance": { "total": 5269.877175295904, "count": 194550, "self": 3.9226199549966623, "children": { "env_step": { "total": 3586.9164053607537, "count": 194550, "self": 3288.0876719458897, "children": { "SubprocessEnvManager._take_step": { "total": 296.40243266790844, "count": 194550, "self": 13.00312432280316, "children": { "TorchPolicy.evaluate": { "total": 283.3993083451053, "count": 187551, "self": 283.3993083451053 } } }, "workers": { "total": 2.426300746955576, "count": 194550, "self": 0.0, "children": { "worker_root": { "total": 5271.284585982936, "count": 194550, "is_parallel": true, "self": 2262.007381403902, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018497169999136531, "count": 1, "is_parallel": true, "self": 0.0005983560001823207, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012513609997313324, "count": 8, "is_parallel": true, "self": 0.0012513609997313324 } } }, "UnityEnvironment.step": { "total": 0.03673992199992426, "count": 1, "is_parallel": true, "self": 0.0005805549997148773, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004937880000852601, "count": 1, "is_parallel": true, "self": 0.0004937880000852601 }, "communicator.exchange": { "total": 0.03369330700002138, "count": 1, "is_parallel": true, "self": 0.03369330700002138 }, "steps_from_proto": { "total": 0.0019722720001027483, "count": 1, "is_parallel": true, "self": 0.0004029859999263863, "children": { "_process_rank_one_or_two_observation": { "total": 0.001569286000176362, "count": 8, "is_parallel": true, "self": 0.001569286000176362 } } } } } } }, "UnityEnvironment.step": { "total": 3009.277204579034, "count": 194549, "is_parallel": true, "self": 69.41472169518829, "children": { "UnityEnvironment._generate_step_input": { "total": 47.75597869695389, "count": 194549, "is_parallel": true, "self": 47.75597869695389 }, "communicator.exchange": { "total": 2688.26708021006, "count": 194549, "is_parallel": true, "self": 2688.26708021006 }, "steps_from_proto": { "total": 203.8394239768313, "count": 194549, "is_parallel": true, "self": 43.445782396516506, "children": { "_process_rank_one_or_two_observation": { "total": 160.3936415803148, "count": 1556392, "is_parallel": true, "self": 160.3936415803148 } } } } } } } } } } }, "trainer_advance": { "total": 1679.0381499801535, "count": 194550, "self": 7.817082630227787, "children": { "process_trajectory": { "total": 289.00952360491897, "count": 194550, "self": 288.42906261991834, "children": { "RLTrainer._checkpoint": { "total": 0.5804609850006273, "count": 6, "self": 0.5804609850006273 } } }, "_update_policy": { "total": 1382.2115437450068, "count": 1387, "self": 878.9900246831871, "children": { "TorchPPOOptimizer.update": { "total": 503.22151906181966, "count": 68403, "self": 503.22151906181966 } } } } } } }, "trainer_threads": { "total": 8.659999366500415e-07, "count": 1, "self": 8.659999366500415e-07 }, "TrainerController._save_models": { "total": 0.09296632800032967, "count": 1, "self": 0.001359346000754158, "children": { "RLTrainer._checkpoint": { "total": 0.09160698199957551, "count": 1, "self": 0.09160698199957551 } } } } } } }