{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5212203860282898, "min": 0.42443421483039856, "max": 1.3526387214660645, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15703.328125, "min": 12760.1904296875, "max": 41033.6484375, "count": 33 }, "Pyramids.Step.mean": { "value": 989981.0, "min": 29952.0, "max": 989981.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989981.0, "min": 29952.0, "max": 989981.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.314923495054245, "min": -0.11415332555770874, "max": 0.314923495054245, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 82.19503021240234, "min": -27.51095199584961, "max": 82.19503021240234, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.5973178148269653, "min": -0.34863272309303284, "max": 0.9896432161331177, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 155.8999481201172, "min": -88.2040786743164, "max": 253.34866333007812, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06800307986573205, "min": 0.06514635926439605, "max": 0.07188785662391961, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9520431181202487, "min": 0.48879172240019964, "max": 1.0507185631968063, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.03302316138170613, "min": 0.00013495565848924354, "max": 0.1775390304995069, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.46232425934388577, "min": 0.001484512243381679, "max": 2.4855464269930967, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.274904717921433e-06, "min": 7.274904717921433e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010184866605090005, "min": 0.00010184866605090005, "max": 0.0032249323250225993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10242493571428575, "min": 0.10242493571428575, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4339491000000004, "min": 1.3886848, "max": 2.3599008, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002522510778571431, "min": 0.0002522510778571431, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003531515090000003, "min": 0.003531515090000003, "max": 0.10751024225999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009589998051524162, "min": 0.009521410800516605, "max": 0.4344307482242584, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13425996899604797, "min": 0.13425996899604797, "max": 3.041015148162842, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 534.0, "min": 534.0, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29904.0, "min": 15984.0, "max": 33673.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.1802142529881425, "min": -1.0000000521540642, "max": 1.1802142529881425, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 66.09199816733599, "min": -31.99760165810585, "max": 66.09199816733599, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.1802142529881425, "min": -1.0000000521540642, "max": 1.1802142529881425, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 66.09199816733599, "min": -31.99760165810585, "max": 66.09199816733599, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.053301877124925214, "min": 0.053301877124925214, "max": 10.074072345159948, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.984905118995812, "min": 2.984905118995812, "max": 161.18515752255917, "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": "1740242619", "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": "1740244880" }, "total": 2261.640177796, "count": 1, "self": 0.5264512859994284, "children": { "run_training.setup": { "total": 0.02031495599999289, "count": 1, "self": 0.02031495599999289 }, "TrainerController.start_learning": { "total": 2261.0934115540003, "count": 1, "self": 1.6608676560454114, "children": { "TrainerController._reset_env": { "total": 2.8096420120000403, "count": 1, "self": 2.8096420120000403 }, "TrainerController.advance": { "total": 2256.5328870959547, "count": 63354, "self": 1.7058390559227519, "children": { "env_step": { "total": 1558.721168220041, "count": 63354, "self": 1379.73045448803, "children": { "SubprocessEnvManager._take_step": { "total": 177.97804317201098, "count": 63354, "self": 5.213186342940617, "children": { "TorchPolicy.evaluate": { "total": 172.76485682907037, "count": 62562, "self": 172.76485682907037 } } }, "workers": { "total": 1.0126705599998331, "count": 63354, "self": 0.0, "children": { "worker_root": { "total": 2255.134067806, "count": 63354, "is_parallel": true, "self": 1003.1274539720421, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0023819359998924483, "count": 1, "is_parallel": true, "self": 0.0006719650000377442, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017099709998547041, "count": 8, "is_parallel": true, "self": 0.0017099709998547041 } } }, "UnityEnvironment.step": { "total": 0.050272484999823064, "count": 1, "is_parallel": true, "self": 0.0005771379999259807, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000434752999808552, "count": 1, "is_parallel": true, "self": 0.000434752999808552 }, "communicator.exchange": { "total": 0.04758188300002075, "count": 1, "is_parallel": true, "self": 0.04758188300002075 }, "steps_from_proto": { "total": 0.0016787110000677785, "count": 1, "is_parallel": true, "self": 0.0003655340005934704, "children": { "_process_rank_one_or_two_observation": { "total": 0.001313176999474308, "count": 8, "is_parallel": true, "self": 0.001313176999474308 } } } } } } }, "UnityEnvironment.step": { "total": 1252.006613833958, "count": 63353, "is_parallel": true, "self": 33.46966695882293, "children": { "UnityEnvironment._generate_step_input": { "total": 23.993327821063986, "count": 63353, "is_parallel": true, "self": 23.993327821063986 }, "communicator.exchange": { "total": 1092.4769454369998, "count": 63353, "is_parallel": true, "self": 1092.4769454369998 }, "steps_from_proto": { "total": 102.06667361707127, "count": 63353, "is_parallel": true, "self": 21.82350451899765, "children": { "_process_rank_one_or_two_observation": { "total": 80.24316909807362, "count": 506824, "is_parallel": true, "self": 80.24316909807362 } } } } } } } } } } }, "trainer_advance": { "total": 696.1058798199911, "count": 63354, "self": 3.223349782016385, "children": { "process_trajectory": { "total": 135.36119856997425, "count": 63354, "self": 135.15033359997437, "children": { "RLTrainer._checkpoint": { "total": 0.21086496999987503, "count": 2, "self": 0.21086496999987503 } } }, "_update_policy": { "total": 557.5213314680004, "count": 441, "self": 304.45378325302386, "children": { "TorchPPOOptimizer.update": { "total": 253.06754821497657, "count": 22827, "self": 253.06754821497657 } } } } } } }, "trainer_threads": { "total": 1.0120002116309479e-06, "count": 1, "self": 1.0120002116309479e-06 }, "TrainerController._save_models": { "total": 0.0900137779999568, "count": 1, "self": 0.0014601789998778258, "children": { "RLTrainer._checkpoint": { "total": 0.08855359900007898, "count": 1, "self": 0.08855359900007898 } } } } } } }